MCP App Store
by KeenEthics
Hyperbound icon

Hyperbound MCP Server for ChatGPT

By Hyperbound

Overview

Connect your existing Hyperbound account to search sales calls and training assets, analyze sales performance, research connected knowledge, and create or update training drafts. Access follows your Hyperbound organization, role, and approved permissions. Review and explicitly approve publication before making drafts live. Requires an existing Hyperbound account; available capabilities depend on your organization and role.

How to connect

  1. ChatGPT: Open the Hyperbound listing in the ChatGPT app directory and choose Connect. ChatGPT listing Hyperbound exposes 21 tools here.

Tools

askKota

ChatGPT
Ask Kota a coaching or performance-analysis question and receive a concise, evidence-grounded answer. Use this tool when the request calls for professional sales coaching judgment, interpretation of Hyperbound performance data, call-analysis guidance, or practical recommendations. Kota can inspect the organization’s available Hyperbound data within the user’s permission scope and synthesize the best advice it can support. This tool is best for questions where the caller needs a complete answer, not raw data extraction. The answer may include links to relevant Hyperbound resources when they help the caller review evidence or take action. Do not use this tool to create or update assets, generate charts, or finalize drafts. It is intended for analysis, coaching, and recommendations. Execution Time This tool takes anywhere from 30 seconds to 2 minutes to execute. Warn the user about the expected wait before calling it. Flow 1. Check whether the conversation, previous results, or a narrower MCP tool can answer the request. 2. Prefer the narrower tool when it can do the job. Use askKota only as a fallback when the request requires Kota's professional sales judgment or practical recommendations. 3. Write a self-contained question with the relevant scope, timeframe, and business context. 4. Warn the user about the expected wait, then call askKota. 5. Present Kota's evidence-grounded answer and any material caveats. Guidelines Do - Prioritize direct, faster tools whenever they can answer the request as well. - Use dataAnalyst for a structured analytical report, searchAssets for a direct bot or scorecard lookup, and searchCalls for transcript-semantic search. - Treat identifiers as continuation data. Prefer names and labeled Hyperbound links. Don't - Do not use askKota as the first choice when existing context or another tool already provides the answer. - Do not expose tool calls, worker details, or MCP plumbing. - Do not add an ID field unless the user explicitly requests one. - Do not claim an asset was created, changed, assigned, reviewed, or published. This tool performs no mutations.

completeTaskItem

ChatGPT
Tool: CompleteTaskItem Completes or changes one item on the active AI chat task, or completes an approved batch of items across the active task and its queued tasks. Completing the final required item automatically completes each task. When to use this tool - The user selected a folder or scorecard in conversation. - The user affirmatively confirmed the exact option you just offered. - A previously completed selection needs to be changed while the task is still active. - The user approved folder or scorecard assignments for multiple creation tasks. When not to use this tool - The required value is unknown or ambiguous. - A single-item call targets a queued or cancelled task, or a completed task not returned in reopenableTasks. - The task item is unrelated to the user's request. Do's - Pass either taskId, taskItemId, and values for one item or completions for a batch, never both. - Use the exact taskId and item id returned by create_agent_v2, create_scorecard_v2, a task mutation, or get_tasks. - When one approval covers multiple tasks, send one completions batch ordered from the active task through queued tasks. Include every required item needed to complete each queued task before advancing to the next one. - Resolve folder and scorecard values with get_task_item_options before completing picker items from conversation. - Pass the selected option value unchanged. Scorecard resource-folder values are strings; agent-folder and scorecard values are numeric. - Send [true] for a confirmation item only after the user explicitly satisfies that item's label. - For a choice item, send exactly one option ID declared in its poll. - Folder selection is optional while a standalone scorecard remains a draft. Selecting its folder item moves the draft without publishing it. - Wait for this result before attempting another dependent task action. One successful batch applies every included selection and advances through the included queue without continuation polls between those tasks. Approval authorizes the action; it does not perform it. - Never say an asset was changed, moved, or made ready unless this tool's successful result confirms that exact action. - A bot publish-decision choice publishes the bot once its remaining required setup is complete. After that successful task completion, do not call finalize_asset for the same bot. - A scorecard publish-decision choice publishes the scorecard once its required folder is selected. If the user previously kept it as a draft, reuse the retained task from reopenableTasks; do not call finalize_asset for the same scorecard. - A newly created learning module first requires its active task's Draft or Publish choice. Publish continues to the assignee/team picker and due-date step; Keep as draft completes the task. For a later publication request, reuse its retained task from reopenableTasks and complete publishDecision with ["publish"] to resume those pickers. Do not recreate the module or publish it separately with finalize_asset while the task is active. - If publication reports that the module is already published but assignment could not be confirmed, explain that partial outcome and check assignments before retrying. Do not claim it remains a draft or use keepDraft to unpublish it. - If the result contains publicationError, the returned task retains the saved selections. Explain that publishing failed, do not ask for those selections again, and stop the action for this turn. Do not call this tool or finalize_asset again to retry publication in the same turn, even if the user had already approved publishing. A new user request can retry the outstanding publish decision. Don'ts - Do not invent task IDs, item IDs, folder IDs, or scorecard IDs. - Do not confirm review merely because the draft was generated. - Do not target a queued task with the single-item form. - Do not skip the active task in a batch. Examples - User: "Use the Cold Call scorecard." → Resolve that scorecard with get_task_item_options, then complete the scorec…

createAgent

ChatGPT
Tool: CreateAgent Creates and persists one or more draft Hyperbound AI roleplay agents. Every requested agent belongs in the agents array and is generated in parallel. Use this tool for new realistic buyer, customer, manager, colleague, or logistics roleplay agents. Use update_agent for existing agents. Input contract - Each agent requires enough information to define its persona, selling context, call type, and scenario. - Always fill description with concise rep-facing practice instructions, including for bite-sized roleplays: the situation the rep is entering, the skill to practice, and the desired outcome. Infer these from the request and supplied context without asking an extra question. Preserve explicit user instructions; do not substitute a generic equipment reminder or reveal hidden buyer information. - This tool does not perform web research. When grounding is needed, complete that research first and pass every relevant finding through prospectDetails, selling, and callContext. - Put all independently creatable agents in one agents array. Do not split one batch across multiple calls. - For a one-by-one multi-agent request, put exactly the current agent in agents. When requested agents remain, also pass oneByOneSequence with the current position, original total, and every remaining agent in order. Omit it only for the final agent. - Ground real people and companies in supplied or researched facts rather than invented details. - Set emotionalState on each agent whenever the user asks for a mood, attitude, or difficulty. When they ask for a mix, give each agent in the batch a different state allowed for its call type. Some call types allow only a few states; when the batch needs more variety than they allow, reuse states and tell the user which agents share one. Describing the mood only in prospectDetails does not change how the bot behaves on the call, so keep prospectDetails consistent with the chosen state. - Standard roleplays use Hyperbound's deterministic call-type opener unless the user explicitly requests a custom opening. Set openerLine only for that explicit request. - Use acceptsPrivateCalls: true and letRepsDecideCallVisibility: false for a private bot whose calls and recordings stay with each caller. - Use both visibility fields as false for public calls, or acceptsPrivateCalls: false and letRepsDecideCallVisibility: true when callers should choose per call. - Call visibility does not control who can discover the bot. Bot discoverability is a separate admin setting. - Set hideLeaderboard: true when the bot should not show a leaderboard on the pre-call or post-call page. - Set tags to the complete tag-name list requested for each bot. Missing organization tags are created and shared tag names can be applied across an entire batch. - This tool creates single-party drafts only. Multi-party roleplays begin as a normal draft and are expanded afterward through update_agent. Bite-sized roleplays Use a bite-sized roleplay when the user wants a short practice session focused on one specific moment, skill, or objection rather than a complete call. - Set biteSizedRoleplay to true. - Set biteSizedRoleplayBotKnowledge to what the buyer already knows when the practice begins, including relevant earlier conversation context. - Set biteSizedRoleplayBotFocus to the single skill, topic, or objection the roleplay should cover before ending. - Set biteSizedRoleplayCallOpener to the exact one-line opening the buyer should say verbatim. - Keep the buyer persona and normal call type realistic. Bite-sized roleplay is a focused behavior, not a separate persona or call type. - Set isVisionEnabled: true as well when the user explicitly requests Vision or wants the bot to see video or shared slides during the roleplay. - Do not call the tool for an obviously bite-sized request until those three bite-sized inputs are known or the user has explicitly asked you to infer them. Result contract - Persists each generated agent as a draft. - Returns every agent hypId and…

createLearningModule

ChatGPT
Tool: Create Learning Module Creates a Learning Module draft through the same Call Progression or builder flow as Kota chat. MCP returns text and links, not chat polls or cards. Flow 1. Ask the user to choose Call Progression or Create from scratch unless they already chose. Call this tool with the corresponding path. Create from scratch saves an empty draft and returns its builder link; stop the guided flow there. 2. For Call Progression, ask which existing bot reps should practice. Use searchAssets to resolve its exact numeric agentId. Do not choose a bot without the user's selection. Call this tool with path: "callProgression" and agentId to retrieve the suggested linked scorecard and the question “Build the stages from this?”. 3. Show the suggested scorecard and ask the user to choose Use this scorecard, Pick a different scorecard, or Create a new scorecard. If they want another, use searchAssets to resolve its exact numeric scorecardId, then call this tool with both IDs and without confirmed to retrieve its criteria. Selecting that scorecard confirms it; do not ask for confirmation again. Creating a new scorecard is a separate workflow; resume only after the user selects one. 4. After confirmation, author one fresh roleplays entry for each exact scorecard section. Ground botKnowledge, botFocus, and callOpener in the returned source persona and that section's criteria. Call this tool with confirmed: true, the same agentId and scorecardId, and all roleplays. This persists the module, one new bite-sized bot and one mini scorecard per section, and a publication task. The source bot and scorecard are unchanged. 5. Give the returned draft's reviewUrl as a labeled preview link. Present the task's Publish and Keep as draft options. Stop unless the user already chose one. 6. Continue the task with completeTaskItem. Publish first records intent, then requires an assignee/team selection and due date. Use getTaskItemOptions to resolve assignees, and complete the final date item with an ISO timestamp including timezone. The final task completion publishes and assigns the module. Keep as draft ends setup without publication. 7. If the user later asks to publish a kept draft, use getTasks with the returned workflow thread and reopen its publishDecision item. Continue its assignee and date steps; do not recreate the module. Guidelines Do - Treat returned workflow states, questions, scorecard context, and task items as authoritative. - Preserve bot and scorecard IDs across calls; use the exact returned section names. - Ask at each unresolved choice and wait for the user's answer. - State that the module remains a draft until the final Publish step succeeds. Don't - Do not call finalizeAsset while the creation task is active or after it completed with Publish. - Do not invent a bot, scorecard, section, assignee, or due date. - Do not show internal IDs to the user. - Do not claim MCP presents a picker, card, or builder inside the client. Text reading tasks When the user asks to create a module containing reading material, call with path: "builder" and textTasks directly. This saves populated sections rather than asking the user to enter the content manually. Each text task requires a sectionName, title and rich-text HTML content. Supported tags are p, br, strong, em, u, h3, ul, ol, li and a. The result includes section/task IDs; reuse them with updateLearningModule to edit text tasks. Save a draft first and publish only with user approval.

createScorecard

ChatGPT
Tool: CreateScorecard Creates and persists one new scorecard as a draft. It also creates the scorecard's AI chat task with optional folder selection and a choice to publish or keep the draft. A folder is required to publish but optional while the scorecard remains a draft. Use this only for creation. The result contains the persisted scorecard draft and its setup task. For a one-by-one multi-scorecard request, create exactly the current scorecard. When requested scorecards remain, pass oneByOneSequence with the current position, original total, and every remaining scorecard in order. Omit it only for the final scorecard. A valid sequence is persisted with the task so completing the current scorecard deterministically offers the next requested scorecard. Scorecard generation rules Importing supplied criteria When the user asks to copy, import, or preserve a supplied scorecard verbatim, transfer its section names, criterion names, grading instructions, descriptions, and order exactly. Map the source fields to the tool structure without shortening, splitting, rewriting, or rejecting compound criteria. Preserve N/A instructions in the grading text and set naEnabled when the source enables an N/A outcome. The design rules below apply to generating new criteria or requested redesigns, not verbatim imports. Generating new criteria Strongly prefer binary yes/no AI grading. Do not introduce range grading or custom weights unless the user requests them; preserve existing grading and weights when updating a scorecard. For default yes/no AI grading, every criterion must be a discrete yes/no check that an AI grader can verify directly against a call transcript. Do not generate one broad question for an entire skill because partial execution must receive partial credit. Follow this process: 1. Name the skill. This becomes the section name. 2. Break the skill into three or four observable behavioral checks. 3. Map each check's label to criterion and its yes/no question to query. 4. Test exactly one behavior per criterion. Split checks that combine multiple conditions. 5. Order checks from a baseline attempt to fuller execution so partial effort earns partial credit. 6. When two reasonable graders could disagree, make the observable passing behavior explicit. Reject criteria containing: - Vague or subjective terms such as "effective", "good", "appropriate", "natural", or "strong" without an exact behavioral definition. - All-or-nothing qualifiers such as "fully", "always", "all", "completely", "throughout", or "any". - Multiple conditions chained into one check. - Outcomes instead of observable behavior, such as "Did the rep build rapport?" rather than the action that constitutes rapport. Before finalizing every section, verify: - A rep who completed roughly half the skill could receive roughly half credit instead of zero. - Every criterion names one specific observable behavior. - Every criterion can be answered yes or no from the transcript. - The resulting score would match what a human listening to the call would give by ear. Default to type: "egpt" and corpus: "both", with a short explanation. Do not generate keyword matching criteria. When the user requests range grading and the tool schema permits erange, use type: "erange" and preserve the requested scale. Supply questions with observable rubric descriptions and numeric grade values, plus a passingGrade within that scale when requested. The yes/no decomposition rules above apply to egpt, not range rubrics. Preserve existing range criteria when updating a scorecard. Custom weights - Only supply scoringConfig when the user requests custom weights. Use exact section names in aggregateScoreWeights.sectionCriteriaWeights, with finite percentage values from 0 to 100. - Section weights plus any statWeights must total exactly 100%. These are percentages, not relative ratios: 2:1:1 is invalid; use 50:25:25. With 20% allocated to stats, sections must total 80%. - On updates, preserve unrelated weights and include the complete allocation w…

dataAnalyst

ChatGPT
Tool: Data Analyst Analyzes information in Hyperbound for the authenticated user and returns a Markdown report. The tool retrieves the permitted Hyperbound records it needs. Execution Time This tool takes anywhere from 30 seconds to 2 minutes to execute. Warn the user about the expected wait before calling it. Flow 1. Check whether the requested information is already available in the conversation or previous tool results. 2. Prefer a narrower MCP tool when it can do the job. Use dataAnalyst only as a fallback when the request requires a new structured analysis. 3. Write one self-contained task in plain language. 4. Include the population, filters, timeframe and timezone, comparison, and desired output when relevant. 5. Repeat important conversation context because the analyst receives only this task. 6. Warn the user about the expected wait, then call dataAnalyst. 7. Present the supported findings, examples, caveats, and unresolved limitations from the report. Guidelines Do - Use this tool for performance or adoption metrics, comparisons, trends, activity summaries, and analysis across calls, reps, teams, bots, scorecards, learning modules, or deals. - Prioritize direct, faster tools whenever they can answer the request as well. - Use searchAssets for a direct bot or scorecard lookup, searchCalls to find calls by what was said, and askKota for conversational coaching. - Preserve material scope and caveats when answering the user. - Prefer names and labeled Hyperbound links over identifiers. Don't - Do not call dataAnalyst to retrieve information already available to you, including IDs, references, names, links, or earlier tool results. - Do not narrate retrieval implementation, worker delegation, or MCP plumbing. - Do not add an ID field unless the user explicitly requests one. - Do not mutate an asset or imply that an asset workflow step occurred.

finalizeAsset

ChatGPT
Tool: FinalizeAsset Publishes one or more persisted draft Hyperbound agents, scorecards, or Learning Modules after user approval. A batch is published concurrently in one tool call. Input contract - Pass either documentType and id for one asset or assets for a batch, never both. - For an agent, pass document type agent and the exact draft hypId. - For a scorecard, pass document type scorecard and its numeric configuration ID encoded as a string. - Scorecard publication revalidates custom weights: section weights plus any stat weights must total exactly 100%. If rejected, explain the error and use update_scorecard to correct the draft with the user's intended allocation before retrying. Do not claim it was published. - For a Learning Module, pass document type learningModule, its exact ID, approved assignees using user:<id> or team:<id>, and the confirmed calendar dueDate as YYYY-MM-DD in the assigning user's timezone. Collect missing assignment details before finalizing. This publishes and assigns the module; it does not change the bot's scorecard or grading behavior. Use update_learningmodule only for edits, never for publication. - When publishing multiple approved drafts, pass every document type and ID in one assets batch. Do not call this tool once per asset. Result contract - Returns the published asset as the source of truth. - A batch returns every published asset as the source of truth. - A published AgentCard refreshes from Draft to Live. Flow 1. Use this for a linked update draft, or for a standalone bot or scorecard whose creation task completed with Keep as draft. Confirm that required setup is complete and the user explicitly asked to publish. 2. If the same request already contains explicit publication approval, use it without asking again. Call finalizeAsset with the exact values returned by the preceding workflow. 3. On success, state that the named asset is live and provide its labeled Hyperbound link. 4. For a batch, report successful and failed assets separately from the returned outcomes. 5. On failure, state that publication did not succeed and retain the last confirmed draft state. Guidelines Do - Call this tool only in direct response to explicit user approval to publish the reviewed draft. - Use one batch call when the user explicitly approved multiple eligible drafts. Don't - Do not infer IDs. - Do not treat folder or scorecard selection, task completion, review, or a returned next action as publication approval. - Do not use this tool for an active standalone creation task or an asset already published by task completion. - Do not display asset, scorecard, task, resource, or other continuation IDs. - Never claim success from an attempted or failed call.

getAssetGuidelines

ChatGPT
Tool: Get Asset Guidelines Returns the organization's guidelines for an asset workflow and the connected sources the user may draw on. Guidelines are written by the organization's administrators and apply to every bot or scorecard created or changed in that workflow. Flow 1. Before the first createAgent or updateAgent call in a conversation, call getAssetGuidelines with workflowType ai_roleplay_bots. Before the first createScorecard or updateScorecard call, use workflowType scorecards. 2. Apply the returned guidelines to the fields you author. Reuse the result for later calls in the same workflow instead of calling again. 3. If the user asks to use a connected source, reuse its retained report and sources. Call researchKnowledgeBase with the matching connector values only for initial retrieval or an explicitly requested new search before authoring the asset. If retained evidence is insufficient, explain the gap and ask whether to search again. Guidelines Do - Treat the returned guidelines as requirements from the organization, not as suggestions. - Mention available connectors only when they are relevant to the user's request. - Refer to connectors by their display name. Don't - Do not skip this call because the request looks simple; guidelines may add requirements the user did not state. - Do not display toolkit values or internal IDs. - Do not call researchKnowledgeBase merely because a connector exists.

getTaskItemOptions

ChatGPT
Tool: GetTaskItemOptions Finds valid folder, scorecard, or people-and-team values before completing a picker task item. When to use this tool - The user names a folder, scorecard, person, or team in conversation. - The user asks you to choose a suitable folder or scorecard for them. - You need a valid option value before calling complete_task_item. When not to use this tool - The picker is rendered in the UI and the user is selecting the value directly. - The task item is a confirmation, string, or number item. - The task is completed or cancelled. Do's - Use the exact active or queued task and item IDs returned by create_agent_v2, create_scorecard_v2, a task mutation, or get_tasks. - Search by the user's requested name when one is provided. - Pass the selected value to complete_task_item unchanged. Scorecard resource-folder values are strings; agent-folder and scorecard values are numeric; people and teams are user:<id> and team:<id> strings. - If the user confirms the exact option you just offered from a successful tool result, reuse that option value and call complete_task_item without searching again. - Ask the user to clarify when multiple options are plausible. Don'ts - Do not invent option IDs. - Do not use an option that is absent from the result. - Do not call this for confirmation, string, or number task items. Examples - User: "Put it in Cold Call Drills." → Search the folder item for Cold Call Drills, then pass the matching value unchanged to complete_task_item. - Assistant: "The AE folder is available. Should I put it there?" User: "Yes." → Reuse the exact AE folder value from the prior successful result and call complete_task_item without searching again. - User: "Choose whichever scorecard fits best." → Retrieve scorecard options, choose only when one clearly matches the bot, otherwise ask the user. Flow 1. Pass the exact task and item IDs returned by asset creation, task mutation, or getTasks. 2. Search by the user's requested name when one was provided. 3. Call getTaskItemOptions before completing a folder, scorecard, or Learning Module assignee picker. 4. Show only the returned option labels. 5. If the user has not already selected exact returned labels, ask them to choose and stop. Agent folder setup and Learning Module assignees accept one or more labels; scorecard folder and scorecard setup accept one. 6. After explicit selection, call completeTaskItem with the corresponding returned value or values without displaying them. 7. For an optional scorecard folder, also offer Skip. After the user explicitly skips it, call completeTaskItem with an empty values array. Guidelines Do - Use only exact returned values with completeTaskItem. - Ask the user to choose when several options plausibly match. - Keep option values as continuation data. Don't - Never auto-select, even when exactly one option is returned. - Do not show option values because they are internal IDs. - Do not invent option IDs. - Do not use this tool for choice, confirmation, string, or number items, or for queued, completed, or cancelled tasks.

getTasks

ChatGPT
Tool: GetTasks Returns the current thread's active task, bounded queue of pending tasks, completed scorecard and learning-module tasks kept as drafts, initiative tasks kept as drafts or cancelled, and fresh persisted state for recently completed asset tasks in recentAssets. When to use this tool - Before changing, completing, or cancelling a task when its current state was not returned by a preceding tool call. - When the user asks what task is active or what work is queued. - After a task transition when you need to verify which queued task became active. - When the user assigns or changes the folder for a standalone scorecard that was previously kept as a draft. - When the user asks to publish a scorecard or learning module that was previously kept as a draft. - When the user asks which assets this thread created or whether a completed asset is currently draft, published, inactive, or deleted. When not to use this tool - When create_agent_v2 or the immediately preceding task mutation already returned the current state. - To retrieve general completed or cancelled task history. reopenableTasks and the bounded recentAssets projection are the only completed-task exceptions. - To search tasks from another chat thread or user. Do's - Change one item only in the active task or the explicitly supported retained drafts in reopenableTasks. A completions batch may include the active task followed by queued tasks. - For a kept scorecard draft in reopenableTasks, change it only when the user explicitly assigns its folder or asks to publish. Folder completion leaves it unpublished. Completing its retained publish decision with ["publish"] reuses an existing folder or reopens it at required folder selection. - For a kept learning-module draft in reopenableTasks, complete publishDecision with ["publish"] to resume its existing assignee/team picker and due-date step. Use those controls instead of free-text questions. The final Publish button publishes and assigns; do not create another module or call finalize_asset alongside the task. - Use the returned task and item IDs exactly as provided. - Call task mutation tools only after identifying the intended active or queued task. - If the conversation and reopenableTasks identify one exact draft, do not search assets or ask for another publishing confirmation. - Treat a matching recentAssets entry as fresh persisted state. resourceId is the task's original asset and currentResourceId is its current published asset when one exists. Don'ts - Do not invent task or item IDs. - Do not use the single-item mutation form for a queued task. Include queued task item IDs only in an approved completions batch that starts with the active task. - Do not use textsearch_assets to rediscover a draft represented in reopenableTasks. - Do not repeatedly poll when no task transition is in progress. Examples - User: "Which bot are we working on?" → Call get_tasks and summarize the active task. - User: "Cancel the second queued bot." → Call get_tasks, identify the intended queued task, then set it to CANCELLED with set_task_status. - User: "Move the draft to Discovery." → Match the retained scorecard task in reopenableTasks, resolve the folder option, and complete its folder item without publishing. - User: "Publish the scorecard I just kept as a draft." → Match the retained scorecard task in reopenableTasks and complete its publish decision with ["publish"]. If it has no folder, wait for the required folder task. Flow 1. Pass the exact threadId returned by createAgent, createLearningModule, or createScorecard. 2. Call getTasks when the preceding call did not return the current state, the user asks what remains, or a queue transition occurred. 3. Treat recentAssets as the fresh persisted lifecycle state for completed creation tasks. Use it to distinguish drafts from assets already published by task completion. 4. Continue only the first outstanding user item on active. Queued tasks wait unless the user asks to switch. 5. For a …

getUserOrganizations

ChatGPT
Tool: GetUserOrganizations Lists the active Hyperbound organizations available to the authenticated user. Use this when the organization context for a request needs to be selected or confirmed. When to use this tool - Discovering which organizations the current user can access. - Resolving a human-readable organization name, such as "HyperDemo", to the numeric orgId required by organization-scoped tools. - Confirming the default organization selected for the current authenticated session. - Preparing a safe orgId override for organization-scoped requests. When NOT to use this tool - Fetching organization analytics, call data, users, scorecards, agents, or performance metrics. - Guessing or fabricating organization access. Only use orgId values returned by this tool. Parameters This tool does not accept parameters. Organization membership is derived from the authenticated user. Result structure The response is JSON with an organizations array. Each organization includes: - orgId: Numeric organization ID to pass to organization-scoped requests. - name: Organization display name. - userId: The authenticated user's user record ID within that organization. - userRole: The authenticated user's role in that organization. - isDefault: Whether this organization is the default context for the current authenticated session. Flow 1. Call getUserOrganizations without arguments to discover the user's memberships and default organization. 2. Match a requested organization name to a returned organization. 3. If the choice is unresolved, show the organization names and ask the user to choose. 4. Use the selected returned orgId as an override in the next organization-scoped tool call. Guidelines Do - Treat membership data as authoritative for the authenticated identity. - Keep organization and user IDs as continuation data unless the user explicitly asks for an ID. Don't - Do not guess organization access or pass an orgId that was not returned by this tool. - Do not imply that listing an organization selected it or performed an organization-scoped action. - Do not use this tool for analytics, calls, users, bots, scorecards, or performance metrics.

listKnowledgeBaseConnectors

ChatGPT
Tool: List Knowledge Base Connectors Lists enabled organization connectors and the caller's authorization status, independently of asset permissions. Flow 1. Call this when the user asks to use connected knowledge. 2. Choose exact toolkit values from the returned catalog for researchKnowledgeBase. 3. Reuse retained findings and sources on follow-ups; research again only when the user explicitly requests another search. Guidelines Do - Use connected knowledge for general analysis as well as permitted asset work. - Load getAssetGuidelines separately before authoring bots or scorecards. Don't - Do not activate or research connectors merely because they exist. - Do not treat access to knowledge as permission to create or modify assets.

researchKnowledgeBase

ChatGPT
Tool: Research Knowledge Base Researches the organization's connected sources, such as Notion, Google Drive, or a custom MCP server, for general questions, analysis, or asset work. Returns a Markdown report with the sources it used. Execution Time This tool takes anywhere from 30 seconds to 3 minutes to execute. Warn the user about the expected wait before calling it. Flow 1. Call listKnowledgeBaseConnectors and choose connector values from its connectors list. For asset work, also load getAssetGuidelines. 2. Write one self-contained task that describes the question, relevant conversation context, and evidence needed. Include workflowType only for bot or scorecard work. 3. Warn the user about the expected wait, then call researchKnowledgeBase. 4. For authorization_required, present each sign-in link, wait for the user to confirm they signed in, and call the tool again with the same arguments. 5. For completed, answer the question or perform the permitted action with the report as context and attribute material choices to their sources. Guidelines Do - Use this tool only when the user asks to use a connected source or the request clearly depends on one. - Repeat important conversation context in the task because the researcher receives only this task. - Present sign-in links as labeled links for the connector's display name. - Retain the report and sources across follow-ups. If the retained evidence is insufficient, explain the gap and ask whether to search again. Don't - Do not call this tool for requests the user can answer directly or that need no external material. - Do not create or update the asset before research completes when the user asked to use a connector. - Do not display toolkit values, internal IDs, or the raw research mechanics. - Do not call this tool again unless the user explicitly requests another search, refresh, or additional retrieval, or confirms sign-in after authorization_required.

searchAssets

ChatGPT
Tool: Text Search Assets Performs fast, ranked full-text search over Hyperbound agents and scorecards. This is the default tool for quick asset lookup when one search over indexed text and filters can answer the question. It searches the asset text indexed in OpenSearch, hydrates every match from the source database under the caller's organization and permissions, and returns a bounded set of scored matches with concise snippets. When to use this tool - Use this tool for agent or scorecard discovery through indexed text and its supported filters. - Use it to resolve an unknown asset before acting on it. Reuse an authoritative identifier already supplied by the conversation or a successful tool result. - Find agents or scorecards by words or phrases found in their names, roles, companies, descriptions, scenarios, personal details, goals, opinions, objections, sections, criteria, or call-type text. - Discover assets when the user describes their contents rather than providing an exact ID. - Narrow full-text matches with exact indexed filters such as document type, owner, lifecycle status, call type, creation, update, or publication time, language, company, job title, gender, emotional state, scenario, assigned scorecard, generation source, public or visible state, scorecard folder, or scorecard default, editability, and builder-only state. - Use the returned hypId values with agent or scorecard tools after confirming the intended asset. When not to use this tool - Do not use it for counts, grouped counts, aggregates, joins, analytics, exhaustive enumeration, or fields that are not indexed. Results are relevance-ranked and bounded, so they cannot establish a reliable count. Use query for those structured database questions. - Do not use query merely to perform a quick text lookup of agents or scorecards that this tool can resolve directly. - Do not use it for call transcripts. Use search_calls for what was said during calls. - Do not treat a missing match as proof that an asset does not exist. Full-text search is relevance-ranked and bounded. - Do not invent unsupported filters or translate a structured database question into keywords. Search semantics - query is the full-text expression. Make it concise but include the distinctive terms that should appear in the asset. - Filters are exact and case-insensitive. Values within one filter are OR conditions; different filters are combined with AND. - A document with no indexed value for a supplied filter remains eligible. A filter excludes only documents whose field has a non-null value that does not match. - documentTypes supports agent and scorecard. Omit it to search both. - Results are ordered by OpenSearch relevance score, then creation time. - The response includes each provider-safe hydrated asset DTO with its relevance score and matching snippet. It is limited to at most 30 results. - Search scores are meaningful only within the same tool call. Do not compare scores across separate searches. Do's - “Find live cold-call bots that mention pricing” → call this tool with the distinctive text plus agent, status, and call-type filters. - “Which scorecards include an opening permission criterion?” → search scorecards for the described criterion and use the returned identifiers for any follow-up action. Don'ts - “How many scorecards does each owner have?” → use query for the grouped database aggregation. - “How many MEDDPIC scorecards do we have?” → use query; a bounded relevance search cannot establish a reliable count. - “How many scorecards exist in total?” → use query. - “Which MEDDPIC scorecards are assigned to agents that had calls last month?” → use query for the joins and call data. Supported exact filters Agents and scorecards - documentTypes: asset type. This filter is always strict; documents never match a different or missing type. - ownerUserIds: agent owner ID or scorecard creator ID. - statuses: agent or scorecard lifecycle status. - callTypes: agent call type or any scorecard call type. - createdFrom / `c…

searchCalls

ChatGPT
Tool: SearchCalls Semantic search over call transcripts. Finds calls based on what was discussed — topics, themes, behaviors, objection types, discovery approaches — not exact keywords. Transcripts are chunked by conversational segment (general discussion, objection handling, discovery, etc.), so results return the specific portion of a call that matched, not the entire transcript. It returns 10 chunks by default; set limit for up to 30. When to use this tool - Finding calls where a specific topic, objection, or sales behavior occurred - Identifying patterns in how reps handle particular situations across multiple calls - Locating examples of good or poor performance on a specific dimension - Answering questions like "show me calls where reps struggled with pricing objections" or "find discovery calls that uncovered the decision-maker" When NOT to use this tool - Looking up calls by a specific user, date, score, team, or other structured attribute — use the Query tool instead - Counting calls, computing averages, or any aggregation — use the Query tool instead - Retrieving scorecard data, agent configurations, or any non-transcript data — use the Query tool instead The distinction: SearchCalls finds calls by what was said. Query finds calls by their metadata. Use both together when you need to find calls matching a behavioral pattern and then retrieve their structured data. For both simulated and real calls, results contain public calls and the authenticated caller's own private calls only. Never use SearchCalls to look for another user's private transcript or infer that no such private calls exist. For objection questions — pricing pushback, competitor objections, timing or budget resistance — the primary source is the structured objection record: Scorecard.objections for simulated calls and RealCallScorecard.objections for real ones. Query those first. They exist for every scored call, classify the objection directly, and do not depend on transcript indexing. Run SearchCalls alongside them to enrich the findings with what was actually said, but never treat an empty semantic result as evidence that no such calls exist — answer from the objection records. For deal-scoped transcript questions, use Query first to get the deal's DealRealCall.realCallId values, then call SearchCalls with callType: "realCall" and callIds set to those IDs. Do not run an org-wide semantic search and manually discard unrelated deals. Parameters - query (string, required): Natural language description of what was discussed. Be specific and descriptive about the topic, behavior, or concept you are looking for. - callType (string, optional): "call" for simulated AI roleplay calls, "realCall" for real recorded calls. Omit to search both types. - callIds (number[], optional): Restrict search to specific call IDs. For deal-scoped searches, first use Query to get DealRealCall.realCallId values for the deal, then pass those IDs here with callType: "realCall". - callerId (number, optional): Filter by user ID of the caller/rep. - teamId (number, optional): Filter by team ID. - minDuration (number, optional): Minimum call duration in seconds. Calls under 100 seconds are excluded automatically. - maxDuration (number, optional): Maximum call duration in seconds. - dateFrom (string, optional): ISO 8601 date. Only include calls after this date. - dateTo (string, optional): ISO 8601 date. Only include calls before this date. Both filter real calls by when they happened (callDate) and simulated calls by when they ran. A real call indexed before the search index stored callDate is filtered by its import time instead, so check each real call's callDate before placing it in a range. When a dated search may have missed such calls, read the IDs of the real calls in the range with Query on RealCall."callDate" and search them by callIds without dateFrom or dateTo. Query quality Search quality depends entirely on how you phrase the query parameter. This is semantic search — it matches on meaning…

setTaskStatus

ChatGPT
Tool: SetTaskStatus Changes an AI chat task to ACTIVE, IN_QUEUE, COMPLETED, or CANCELLED and returns every task changed by the queue transition. The transition is atomic. Making a queued task active moves the previous active task back into the queue. Completing, cancelling, or queueing the active task promotes the oldest other queued task when one exists. When to use this tool - The user asks to switch to a different queued task. - The user asks to pause the active task and continue another task. - The user explicitly asks to cancel or abandon a task. - A workflow must be force-completed even though required task items remain. When not to use this tool - A folder, scorecard, confirmation, string, or number item needs to be completed. Use complete_task_item. - The final required item was just completed. The task completes automatically. - You do not know which task the user means. Call get_tasks or ask for clarification first. - The task is already completed or cancelled and the requested status differs. Terminal tasks cannot be reopened. Do's - Use the exact task ID returned by create_agent_v2, a task mutation, or get_tasks. - Use ACTIVE to switch control to a queued task. - Use IN_QUEUE to pause a task without cancelling its draft. - Use COMPLETED only when the workflow should end despite outstanding items. - Use CANCELLED only when the user explicitly wants to abandon the task. - Treat every returned task state as authoritative. Don'ts - Do not use COMPLETED to publish an asset. Publishing remains a separate action. - Do not use CANCELLED for a revision, review, or temporary pause. - Do not invent task IDs or assume queue order. - Do not call multiple status changes in parallel for the same thread. Examples - User: "Work on the renewal bot instead." → Call get_tasks, identify that queued task, then set it to ACTIVE. The previous active task returns to IN_QUEUE. - User: "Pause this bot for now." → Set the active task to IN_QUEUE; the oldest other queued task becomes active when available. - User: "Cancel the second queued bot." → Identify the exact task and set it to CANCELLED. - A task must end without its remaining items → Set it to COMPLETED, then explain any completion yield returned by the task. Flow 1. Tell the user which named asset tasks changed and report every returned task's new state, including tasks moved back to IN_QUEUE. 2. Explain what a newly active task still requires. For a picker, retrieve labels, ask for an explicit choice, and stop. Guidelines Do - Use completeTaskItem for normal folder, scorecard, confirmation, string, or number selections. - Use COMPLETED only when the user intends to end the workflow despite unresolved items. - Use CANCELLED only when the user explicitly wants to abandon the workflow. Don't - Do not display task, resource, thread, asset, or next-action IDs. - Do not issue parallel status changes for the same workflow. - Do not try to reopen a terminal task. - Do not imply that completing or cancelling a task published an asset.

switchCurrentOrganization

ChatGPT
Tool: Switch Current Organization Makes one of the authenticated user's Hyperbound organizations current for subsequent MCP requests. Each organization may expose a different set of MCP tools based on its configuration and the user's role. Switching organizations refreshes the available tool list. Flow 1. If the user requests an operation whose required tool is unavailable in the current organization, consider whether they intend to perform it in another organization before saying it cannot be done. 2. Call getUserOrganizations and identify the organization the user requested or intended for the operation. 3. If the organization is ambiguous, show the organization names and ask the user to choose. 4. Call switchCurrentOrganization with the exact orgId returned for that organization. 5. Refresh the available tools and continue only with tools exposed for the selected organization. Guidelines Do - Use only an orgId returned by getUserOrganizations. - Remember that different organizations may expose different tools. - When a user-requested tool or capability is unavailable, check whether switching to the intended organization would make it available. - Tell the user which organization is now current after the tool succeeds. - Refresh the available MCP tools after switching because organizations may expose different workflows. Don't - Do not guess an organization ID or switch organizations without a clear user request. - Do not conclude that a requested capability is unavailable everywhere based only on the current organization's tool list. - Do not claim the switch succeeded unless this tool returns success. - Do not use this tool merely to run one operation in another organization when that tool accepts an orgId override.

updateAgent

ChatGPT
Tool: UpdateAgent Creates or reuses the real draft for one existing persisted agent, saves the requested changes there, and returns the saved draft AgentDto. Use create_agent_v2 for a new agent. This tool requires the exact published or draft agent hypId. Input contract - Include only fields that need to change. Omitted fields remain unchanged. - Do not send lifecycle status. The live agent remains unchanged until its draft is published. - Preserve grounded details that are unrelated to the requested change. - supportingAgentInfo replaces the complete supporting-participant list. Supply zero to three participants with names, roles, genders, emotional states, and grounded persona details. A participant's call scenario inherits the primary agent's scenario when omitted. Send an empty list to return the draft to a single-party roleplay. The tool assigns compatible voices and avatars. - Use openerLine for a standard roleplay opener. For a bite-sized roleplay, use biteSizedRoleplayCallOpener for the exact one-line opening and preserve its existing knowledge and focus unless the user asks to change them. - Set isVisionEnabled when the user asks to enable or disable Vision, including for a bite-sized roleplay. Preserve it otherwise. - To make a bot private, set acceptsPrivateCalls to true and letRepsDecideCallVisibility to false. Its calls and recordings then stay with each caller. - To make calls public, set both visibility fields to false. To let callers choose per call, set acceptsPrivateCalls to false and letRepsDecideCallVisibility to true. - Call visibility does not control who can discover the bot. Bot discoverability is a separate admin setting. - Set hideLeaderboard to true when the bot should not show a leaderboard on the pre-call or post-call page. - Set tags only when tags should change. It replaces the complete tag set, creates missing organization tags, and accepts an empty array to clear all tags. - Set folderIds only when bot folder membership should change. Pass the complete desired set of existing numeric folder IDs, preserving unrelated folder memberships. The change is saved to the draft and takes effect when published. Result contract - Returns the persisted before-and-after agent snapshots. Derive displayed changes from those snapshots. - Linked update drafts can be reviewed and published separately; standalone creation drafts remain governed by their existing task. - Returns the persisted draft as the source of truth. Publishing is a separate action. Agent quality examples These examples show the expected realism, specificity, and internal consistency of an agent configuration. They are quality references, not literal tool-call payloads. When updating an existing agent, pass its real hypId and only the fields that need to change. Example 1: Strategic sales leader ```json { "firstName": "Jane", "lastName": "Bowen", "gender": "FEMALE", "jobTitle": "Director of Sales", "personalDetails": [ "You have led the sales organization at Agile Solutions for four years after managing a regional team at a competing CRM vendor.", "You started as an account executive, so you quickly recognize whether a rep understands enterprise sales fundamentals.", "You are concise with vendors and only share internal metrics when the question has a clear business purpose." ], "companyName": "Agile Solutions", "companyDetails": [ "Agile Solutions is a Series C B2B SaaS company with approximately 100 employees.", "The company helps software teams implement and maintain agile project-management workflows.", "The company is prioritizing efficient growth after reducing its sales-technology budget by 10%." ], "companyOrgStructure": [ "You report to the Chief Revenue Officer.", "Five SDR managers report to you.", "The sales organization has approximately 50 SDRs and 50 account executives." ], "goals": [ "Increase qualified pipeline without adding headcount.", "Improve SDR ramp time from four months to three months.", "Prove measurable ROI before renewing or adding sales tools." ], "opi…

updateLearningModule

ChatGPT
Tool: Update Learning Module Edit an existing Learning Module draft, including adding or editing text reading tasks. Published modules are edited through a separate linked draft; this tool never publishes or changes existing assignments. Flow 1. Use the exact module ID. Resolve existing section and task IDs from the module document using the Data Analyst when needed. textTasks accepts a title and rich-text HTML body plus exactly one sectionId or sectionName. Omit taskId to append; supply an existing TEXT taskId to replace its title/body. A new sectionName creates a section. For new tasks, set beforeTaskId to place guidance before an existing roleplay; otherwise the task is appended. Other tasks and sections are preserved. Supported HTML includes paragraphs, bold, italic, underline, h3 headings, lists and links; unsafe markup is removed. 2. Return the saved draft's reviewUrl as a labeled preview link and summarize the edits. The result includes sections and task IDs for follow-up edits. Publish only after explicit user approval, using finalizeAsset for a linked draft or the existing creation task when one exists. For a standalone builder draft without a task, finalizeAsset requires assignees and a due date. Guidelines Do - Reuse returned textTasks references for follow-up edits. - Treat saves as draft changes and preserve unrelated tasks. Don't - Do not overwrite a bot, quiz or call blitz task with text. - Do not invent section/task IDs or publish without approval.

updateScorecard

ChatGPT
Tool: UpdateScorecard Updates one existing persisted scorecard. Content changes create or reuse its draft; folder moves take effect immediately on the scorecard and its draft. Pass the exact numeric scorecardId. For content changes, pass the complete updated config and preserve fields the user did not ask to change. For a folder-only move, omit config. Pass either an exact folderId, a folderName to resolve an existing scorecard folder, or folderId: null to remove the folder. Never invent a folder ID or create a folder unless requested. Folder moves do not require a creation task or publication. Content changes to a live scorecard remain unpublished until its draft is published. Scorecard generation rules Importing supplied criteria When the user asks to copy, import, or preserve a supplied scorecard verbatim, transfer its section names, criterion names, grading instructions, descriptions, and order exactly. Map the source fields to the tool structure without shortening, splitting, rewriting, or rejecting compound criteria. Preserve N/A instructions in the grading text and set naEnabled when the source enables an N/A outcome. The design rules below apply to generating new criteria or requested redesigns, not verbatim imports. Generating new criteria Strongly prefer binary yes/no AI grading. Do not introduce range grading or custom weights unless the user requests them; preserve existing grading and weights when updating a scorecard. For default yes/no AI grading, every criterion must be a discrete yes/no check that an AI grader can verify directly against a call transcript. Do not generate one broad question for an entire skill because partial execution must receive partial credit. Follow this process: 1. Name the skill. This becomes the section name. 2. Break the skill into three or four observable behavioral checks. 3. Map each check's label to criterion and its yes/no question to query. 4. Test exactly one behavior per criterion. Split checks that combine multiple conditions. 5. Order checks from a baseline attempt to fuller execution so partial effort earns partial credit. 6. When two reasonable graders could disagree, make the observable passing behavior explicit. Reject criteria containing: - Vague or subjective terms such as "effective", "good", "appropriate", "natural", or "strong" without an exact behavioral definition. - All-or-nothing qualifiers such as "fully", "always", "all", "completely", "throughout", or "any". - Multiple conditions chained into one check. - Outcomes instead of observable behavior, such as "Did the rep build rapport?" rather than the action that constitutes rapport. Before finalizing every section, verify: - A rep who completed roughly half the skill could receive roughly half credit instead of zero. - Every criterion names one specific observable behavior. - Every criterion can be answered yes or no from the transcript. - The resulting score would match what a human listening to the call would give by ear. Default to type: "egpt" and corpus: "both", with a short explanation. Do not generate keyword matching criteria. When the user requests range grading and the tool schema permits erange, use type: "erange" and preserve the requested scale. Supply questions with observable rubric descriptions and numeric grade values, plus a passingGrade within that scale when requested. The yes/no decomposition rules above apply to egpt, not range rubrics. Preserve existing range criteria when updating a scorecard. Custom weights - Only supply scoringConfig when the user requests custom weights. Use exact section names in aggregateScoreWeights.sectionCriteriaWeights, with finite percentage values from 0 to 100. - Section weights plus any statWeights must total exactly 100%. These are percentages, not relative ratios: 2:1:1 is invalid; use 50:25:25. With 20% allocated to stats, sections must total 80%. - On updates, preserve unrelated weights and include the complete allocation when changing weights. Renaming, adding, or removing weighted sectio…

upsertFolder

ChatGPT
Tool: Upsert Folder Creates a new bot or scorecard folder, or renames an existing folder. When to use this tool - Use it only when the user explicitly asks to create a folder or rename a folder. - To create a root folder, omit both folderId and parentFolderId. - To create a nested folder, omit folderId and pass the existing parent folder's ID as parentFolderId. - To rename a folder, pass its existing ID as folderId and omit parentFolderId. Guidelines - Set type to agent for bot folders and scorecard for scorecard folders. - Use only an authoritative folder ID returned by a tool or provided by the application. - Never create a folder merely because an agent or scorecard needs folder selection. Tell the user folder creation is available, then wait for an explicit request. - Never infer a parent folder when the requested nesting is unclear. - This tool does not move folders. - Team access applies only to root scorecard folders, and their subfolders inherit it. Pass teamIds only when the user names the teams who should see the folder; without them a new folder is open to everyone and a renamed folder keeps its teams. Pass an empty teamIds only when the user asks to open the folder to everyone. - Do not expose folder IDs in user-facing text. Flow 1. Call upsertFolder only after the user explicitly asks to create a folder or rename a folder. 2. Set type to agent for bot folders or scorecard for scorecard folders. 3. To create a root folder, pass the requested name and omit both folder IDs. 4. To create a nested folder, pass the authoritative existing parent ID as parentFolderId and omit folderId. 5. To rename a folder, pass its authoritative existing ID as folderId and omit parentFolderId. 6. Tell the user whether the folder was created or renamed. If this was part of an active agent or scorecard setup, call getTaskItemOptions again before offering or selecting the new folder. Guidelines Do - Clarify whether the folder is for bots or scorecards when the request is ambiguous. - Use folder IDs only as tool continuation arguments. - Treat the returned operation and folder state as authoritative. Don't - Never call this tool merely because an agent or scorecard requires folder selection. - Do not infer that mentioning a nonexistent folder is permission to create it; ask first. - Do not display folder IDs. - Do not use this tool to move folders or change visibility.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/hyperbound"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/hyperbound)