Search live directory results

AgentBroko gives AI agents reusable skills for creating content, processing files, generating videos and PDFs, and automating repeatable tasks. Build once, reuse across projects, and give your agents practical capabilities they can run locally.

AgentBroko

By Broke Innovation

Prompts: 3

AgentBuild is an agent-first website builder. It gives the agent you already use the tools to design, build, and manage your website through chat, without requiring a separate website editor. Describe your business; it creates the site from curated sections and templates, adds your content, and deploys a preview for review. Nothing is published to your domain until you approve it. Connect a domain you own, and AgentBuild handles the site connection, DNS records, and email setup. After launch, ask your agent for changes whenever you need them. Hosting, structured data, core SEO, traffic and lead reporting, and rollbacks are included.

AgentBuild

By AgentBuild, Inc

Tools: 59 · Prompts: 3

AgentCollect's public MCP connector lets Claude query your accounts-receivable recovery data. It exposes one read-only tool, ask-ar-analyst, which answers natural-language questions about outstanding invoices, collection status, disputes, and recovery performance. Access is scoped to your own account via OAuth (dynamic client registration, PKCE S256, scope mcp:read) and no data is modified.

Finance

AgentCollect

By Respaid Inc (dba AgentCollect)

Tools: 1

Fivetran's Agent Context MCP provides AI agents the full breadth of business context needed to answer questions and take action, reliably. Built on Fivetran's open context layer, it infers and curates context from every enterprise system — including data sources, schemas, concepts, knowledge bases, and analytical metadata — and exposes it through the Model Context Protocol. Agent Context MCP powers natural-language search, data-aware assistants, coding workflows, and custom AI applications. Its standard MCP interface makes it easy to bring rich, trusted, and comprehensive business context into the AI tools teams are already using, including Claude, ChatGPT, coding agents, and custom applications.

AgentContext

By Fivetran Inc.

Tools: 2

AgentCron is your team's Collaborative OS. Plan. Execute. Measure. Bring your team's work into the conversation. Find projects and tasks, summarize progress, create or update task cards, organize Drive files and folders, and read or send workspace messages. Turn a conversation into work your team can see and act on. Connect your AgentCron account with OAuth, choose a workspace and approve access. The connector follows your existing workspace and resource permissions. Disconnect it in AgentCron Settings > Connected apps. An AgentCron account and workspace are required. A free plan is available. This connector works with AgentCron's projects, boards, cards, files and chat; it does not process payments or replace the full AgentCron interface.

AgentCron

By Gocnet Technologies LLP

Tools: 21

Research any company and the people who work there, without leaving ChatGPT. Look up a company by its website to see what it does, who it sells to and how, its tech stack (more than 3,000 technologies tracked, each with how and when it was detected), its email format and general inboxes such as sales@ and support@, address and phone where listed, recent tool changes and similar companies. Find people at a company or in a role, with their job titles and LinkedIn profiles, taken from the company's own team and about pages. Build prospect lists by technology, industry, business model, or B2B and B2C, for example B2B software companies that use HubSpot, and see which companies recently started or stopped using a tool. Useful for account research before a sales call, building target lists and understanding a competitor's customers. About 9 million companies are fully profiled, and any other company website is profiled on request, usually within a few minutes. AgentData only reads data: it never sends messages or changes anything. Data comes from public web pages, DNS records and HTTP headers. Our crawler respects robots.txt and identifies itself. Anyone can ask for their data to be removed at agentdata.run/legal/data-removal.

Business & Operations

AgentData

By DragApp.com Ltd

Tools: 6 · Prompts: 3

Explain AgentDust process and disk reports that users provide, and guide local setup. This skills package does not connect to a Mac or provide live process access. Live inspection requires a separately configured local AgentDust MCP connection. Cleanup requires AgentDust's own typed approval.

AgentDust

By Hamza Hamidi

Prompts: 3

Agent Grid connects Claude to a collaborative workspace where AI agents and humans can create, upload, view, update, and share interactive artifacts such as documents, designs, prototypes, front-end experiences, and presentations. Related artifacts can be grouped into shared workspaces, while human ownership, agent authentication, granular permissions, and team-based entitlements keep collaboration governed and secure. It is like Google Drive but built for Agents and Humans.

AgentGrid.io

By Anima App Inc.

Tools: 9

Built for GPT, Codex, Claude, Grok Bot (GrokBot), Hermes, OpenClaw, Cursor: Humans and agents work on the same Brain, live Artifacts, Docs, Reports, Slides, Apps, Websites, Designs, with Shared Context such as Second Brain with full version history and access control.

Business & Operations

AgentGrid.io - Shared Drive

By Anima App

Tools: 15 · Prompts: 2

AgentMail gives AI agents their own email inboxes. Through this connector, an agent (or you, in ChatGPT) can spin up a dedicated inbox on the fly, then send, receive, reply to, and forward email, with full thread context, drafts, and attachments, entirely through tool calls. Unlike traditional email APIs built for one-way notifications, AgentMail is built for two-way conversations: an agent can read an incoming thread, understand it, and respond in context, just like a person would. This makes email a first-class communication and identity channel for agents, letting them sign up for services, coordinate with people, and talk to other agents. Key capabilities exposed over MCP: • Inboxes: create, list, get, update, and delete agent inboxes • Messages: send, reply, forward, list, and update • Threads: list, read, label, and delete full conversation threads • Search: full-text search across threads and messages • Drafts: create, list, read, update, send (with scheduling), and delete • Attachments: retrieve attachments by ID, with text extraction for PDF/DOCX Connect in seconds via OAuth using your AgentMail console identity. No API key required in ChatGPT. Sign up free at console.agentmail.to.

AgentMail

By AgentMail, Inc.

Tools: 43 · Prompts: 3

AgentMailer gives every AI agent a durable identity with a unique @agentmailer.ai handle. Agents can send and receive email with people, services, and other agents without borrowing a human inbox. Agents can also communicate directly through A2A, a standard for discovering another agent’s capabilities and exchanging structured messages, tasks, progress updates, and results. This makes AgentMailer useful for long-running loops and managed agents in Claude that need to delegate work, coordinate with other agents, and preserve communication across sessions. Through Claude, users can create and manage agent inboxes, search messages and complete threads, access attachments, prepare drafts, send replies, and coordinate agent-to-agent work. Organization-scoped permissions and explicit approval for external actions keep people in control.

Communication

AgentMailer

By Aadi Labs

Tools: 32

agentmarkup generates the machine-readable layer of a website at build time: llms.txt, JSON-LD structured data, markdown mirrors, AI-crawler robots.txt rules and Content-Signal headers, then validates what the build actually produced. It works out which layer owns your final HTML and installs the matching adapter rather than guessing from what is already in package.json: Vite, Astro, Next or Nuxt, plus a framework-agnostic CLI for any other directory of built HTML, and core helpers for custom pipelines and dynamic SSR routes. Inspecting your repo is read-only. Before installing a package, writing config, running a build, or making an outbound request to a deployed site, it stops and presents a single plan naming the package, every file that would change, and the exact commands. Validation is deterministic: a missing required field is an error, a missing recommended field is a warning. There is no score, grade or percentage. Existing curated llms.txt, robots.txt, _headers and JSON-LD are preserved unless you explicitly opt into replacement. Open source and MIT licensed.

AgentMarkup

By Anima Felix

Prompts: 3

AgentPricing Connector è il collegamento tra Claude e AgentPricing per gli agenti immobiliari. Da chat puoi preparare valutazioni, confrontare venduti e annunci, verificare un prezzo richiesto, analizzare il mercato locale e riaprire i report esistenti. Serve un account AgentPricing autenticato.

AgentPricing Connector

By AgentPricing

Tools: 32

Starts a new instrumented Codex CLI session and leaves a local, hash-only receipt of command events and checked repository states. Later, AgentProof validates the receipt and compares its recorded final file commitments with the current repository. The child runs non-interactively with Codex approvals disabled and retains the selected read-only or workspace-write sandbox. It does not capture the current Codex conversation or establish completeness, truth, authorship, work quality, compliance, payment authorization or settlement, and it uses no HREVN service or credential.

AgentProof

By Miguel Herrero Burgos

Prompts: 3

AgentRoam helps travelers find and buy travel eSIM data plans with stablecoins and crypto. Choose your destination, compare available plans, pay from your wallet, and receive your eSIM setup details by email after checkout. You can also explore crypto-friendly travel gift cards and airtime top-ups. AgentRoam is built for both travelers and AI agents, with MCP support for searching destinations, comparing plans, preparing checkout quotes, and tracking order status with user confirmation before purchase.

Travel

AgentRoam

By Yariv Adin

Tools: 11 · Prompts: 2

AgentTrust looks up an AI agent by the exact URL you are about to call and returns what AgentTrust has observed about it: the agent's current health status, whether the endpoint's ownership has been verified, its reliability score from AgentTrust's own monitoring history (when one is available), and a trust decision with a recommendation, a confidence level and the reasons behind it. The connector has one tool, check_agent_trust. It is read-only and needs no AgentTrust account or API key. It never contacts the endpoint being checked: it only reads the monitoring data AgentTrust has already collected about public agents, including agents registered by their owners and MCP servers listed in the official MCP Registry. If AgentTrust has not observed a URL, the result says so ({ matched: false }) rather than guessing. A trust decision is a signal derived from AgentTrust's observations, not a certification or a guarantee that an agent is safe, so treat it as one input alongside your own judgment. URLs must be absolute http:// or https:// addresses, and anonymous checks are rate-limited. Each check records minimal usage data (no raw IP addresses or full URLs); see the privacy policy for details.

Developer-Tools

AgentTrust

By AgentTrust

Tools: 1

AgentUI Apps lets Claude create and manage data apps in your AgentUI workspace. A data app is a hosted database with tables and records, without a website. What you can do: - Create an app and define its tables and fields (text, numbers, dates, emails, lists and more). - Change a table later: add, rename or remove fields. Existing records are migrated for you. - Find, count, create, update and delete records, one at a time or up to 200 per call. - Write programs: short steps of code that read and write your app's data. Run them on demand, on a schedule, from a webhook, or when an email or WhatsApp message arrives. Each run returns step-by-step logs. Every app you open also comes with its own MCP connector URL, so you can share just that app's data with another tool. Deleting a table or removing a field needs an explicit confirmation. Read-only tools are marked so Claude can use them without asking. You need an AgentUI account to connect. Sign in with OAuth; Claude only sees the apps in your workspace.

Developer-Tools

AgentUI Apps

By AgentUI

Tools: 21

AgentWorld Explorer connects ChatGPT to a live, persistent digital civilization of 2,000+ autonomous AI agents that work jobs, trade, negotiate, and settle USDC on the Base blockchain. Use it to answer questions like: How many agents are live right now? What is the treasury balance and wealth distribution (Gini)? Who are the top agents by reputation? What open jobs are agents working? What is a specific agent's current credit standing? What companies are leading the Venture business-simulation game? The plugin exposes 18 free, read-only tools: live economy telemetry, city statistics, the agent roster and profiles, job board browsing, crypto/AI news from the CCN wire, the SolvScore agent credit bureau (trust scores, credit limits, on-chain work attestations), agent liquidity checks, and Venture game market and leaderboard data. Intended users: AI-agent developers, crypto researchers, and anyone curious about the agent economy. All data is public on-chain telemetry. Limitations: strictly read-only (no agent creation or write actions); account setup happens separately on agentworld.me; Venture gameplay numbers (cash, revenue, score) are simulated units for the business-sim game, not currency.

AgentWorld Explorer

By AgentWorld

Tools: 18 · Prompts: 3

Sales insights to close deals

Business

Agentforce Sales

By Salesforce

Tools: 0 · Prompts: 3

AgentiSend is a transactional email API for AI agents: send through verified domains, with a budget each sender cannot exceed and a kill switch a person can flip. The hosted MCP server at https://api.agentisend.com/mcp exposes 81 tools (43 on tools/list; the rest via list_more_tools). A send is one message or a batch of up to 500 items with per-item results. preflight_email runs every gate a real send runs, sends nothing, and costs nothing. Every 4xx returns code, message, and fix. There is no tool for unsolicited mail. Auth is a bearer API key or OAuth 2.1 with dynamic client registration. Starter prompts: "Send this receipt to the customer." "Preflight this send and tell me what would stop it." "What can I spend today?"

AgentiSend

By WarmySender

Tools: 42 · Prompts: 3

Agentibus runs AI sales agents for coaches, course creators and education businesses. The agent replies to every lead on Instagram DMs, WhatsApp, Messenger, web chat and email, qualifies them against your criteria and books sales calls into your calendar. Across our customers it has booked more than 7,000 sales calls and handled more than 70,000 leads. With this connector you run your agent from Claude: - Pipeline: list your leads, read any conversation, see funnel metrics, bookings and time saved. - Approvals: in hybrid mode every reply waits for you. Review the drafts, then approve or discard them. Approving a reply, discarding a draft and cancelling follow-ups first return a preview of the exact action and run only after you confirm. - Control: pause or resume an agent, take over a single lead by hand, cancel the follow-ups scheduled for a lead. - Knowledge: add a web page or a text (FAQ, price list) to what your agent knows, and test the agent in a sandbox before it talks to real leads. The connector needs an Agentibus account. You sign in with OAuth, act only on your own workspace, and every action is recorded under your name. New to Agentibus? Your first 10 booked sales calls are free: start at agentibus.ai.

Sales-And-Marketing

Agentibus

By Agentibus OÜ

Tools: 19

Agentic Atlas helps you design and review agent systems: skills, subagents, plugins, hooks, and multi-agent workflows. Connect it, then ask Claude a design question in plain language. Claude looks up the patterns that fit your situation and answers from their published rulings, which you can check on agentic-atlas.dev. Reach for it while a design decision is still open: splitting a system into skills, subagents, or tools; deciding what a subagent carries in and hands back; keeping context lean in a long-running workflow; placing a verification step so a wrong answer gets caught; or reviewing a skill or plugin you have already written. Each pattern states a ruling, a worked example, and its links to related patterns. Every ruling links to the decision record that settled it, and every entry carries a maturity label, so you can tell field-tested advice from advice still earning its evidence. A glossary defines the working vocabulary, and a curated eight-step tour is the place to start. The connector is public and read-only. There is no sign-in, account, or payment, and it never writes anything. Setup and the full tool reference: https://agentic-atlas.dev/connect

Agentic Atlas

By Avery Jones

Tools: 5 · Prompts: 3

◆ LECTURER / TEACHER CONTROL • You retain every consequential decision. The Course Redesign Orchestrator is the sole lecturer-facing interface. ◆ SPECIALIST TEAM (10) • Course Mapper and Learning-Outcomes Auditor; Active-Learning Researcher; AI Integration and AI-Competence Researcher; Student Experience, Accessibility and Workload Proxy Critic; Assessment and Constructive-Alignment Designer. • Source Verification and Citation Auditor; Evidence and Feasibility Red Team; Learning Designer; Learning Material Designer; Artefact Accessibility and Visual QA Auditor. The student-experience role is a design-review proxy and never authorises identifiable student data. ◆ GATED WORKFLOW • Gate 0A: verify ownership/processing authority, sensitivity, student data, protected assessment and environment before any source path or content. • Gate 0: confirm sources, rights, tools and egress. Gate 1: confirm the course brief and a fresh run. • HITL 1: approve focus after preliminary mapping. Research, source verification, cross-specialist synthesis, assessment integration and red-team review lead to HITL 2. • Gate 3: approve the integrated blueprint and file plan. Material production creates only approved working copies, followed by evidence, accessibility, visual, alignment and assessment-security QA. • Verify production handoff before HITL 3; accept, revise or reject each artefact. • Request or decline final system review; the accepted run becomes complete and dormant until a later manual or separately approved scheduled trigger creates a fresh run. ◆ DECISION DIALOGUE • One unresolved question at a time. • Use a card only if the live host can show the complete option set plus custom answer. Verified current Codex in Plan mode: 2–3 explicit choices plus automatic Other. • If capacity is unknown, unavailable or exceeded, use ordinary chat with every valid numbered option plus Other, then wait. Never prune, hide or combine valid options to fit a card. • Long sets may use dependency-based chunks with every option visible; the lecturer may split, merge, reorder or rename them. • Preserve custom answers verbatim, show editable recaps, never preselect recommendations and fail closed on uncertainty. ◆ BOUNDARY • The plugin does not register schedules, start runs, publish content, add connectors or change permissions.

Education & Research

Agentic Course Redesign

By GIAN PETER OCHSNER

Prompts: 3