MCP App Store
by KeenEthics
Reos icon

Reos MCP Server for Claude and ChatGPT

By Reos

Overview

Reos is a user-research platform. Teams bring interview recordings, transcripts, documents and survey data into Reos, and Reos turns them into evidence-backed observations, insights and recommended solutions. This connector brings that workspace into Claude. With Reos connected, Claude can: - Answer questions about your research with the exact observations, insights and documents behind each claim, each linked back to Reos. - Search across projects, or read everything one participant said. - Read an interview transcript with timecodes, look at a still frame from a recording, and read the comments and markers your team left on it. - See where each project stands, from raw data to observations, insights and solutions. - Add raw data by pasting text or importing a public URL, start an analysis run and read its results when it finishes. - Create a project or save a write-up as a Reos document, and edit or remove observations and insights. How access works: you sign in to Reos and choose one organisation to connect. Claude acts as you, with the permissions your role has there, and only reaches projects you can already open. Viewers get reading tools only. Every tool that changes your workspace asks before it runs. You can revoke access at any time under AI assistants in your Reos profile menu. Reos is for researchers, designers and product teams who already keep their research in Reos and want to query and act on it without leaving Claude.

How to connect

  1. Claude: Open the Reos listing in the Claude connectors directory and choose Connect. Claude listing Reos exposes 25 tools here.
  2. ChatGPT: Open the Reos listing in the ChatGPT app directory and choose Connect. ChatGPT listing Reos exposes 25 tools here.

Tools

add_text_resource

ChatGPT
Add a piece of raw data to a project by pasting text directly (interview notes, a transcript, a document body). Stored as a text resource and ready to analyse immediately - no download wait. Text must be 50–100,000 characters. Use add_url_resource instead to import from a link.

add_url_resource

ChatGPT
Add a piece of raw data to a project by importing it from a public HTTP(S) URL (a recording, document, or media file). The resource is created as 'pending' and the download runs asynchronously - poll get_project_status until it's ready before running a flow over it. Leave type unset unless the user said what the file is; it then defaults to 'document', which is right for PDFs, papers, articles and web pages. Use add_text_resource for pasted text. Private/internal URLs and Reos's own pages are rejected.

create_document

ChatGPT
Create a new freeform Document in the current project from a draft you've written. Use this for ad-hoc requests where no Document Type template applies (e.g. 'draft a one-pager comparing X and Y', 'write a custom readout of this conversation', 'turn what we just discussed into a document'). Pass title and content (full markdown body that you draft yourself based on the conversation, search results, and selected entities). The Document is persisted in the project's Documents list as type='custom' and the chat reply links to it. For templated kinds of document (summary, evaluation, critique, tips, analysis), use start_flow_run with outputType: "documents" and a documentTypeId instead — that runs the configured flow over project inputs and is the right path whenever a Document Type already covers what the user wants.

create_project

ChatGPT
Create a new research project in this organisation. Provide a name (required) and a short description. Defaults: type='user_research', status='active', priority='medium', size='m' - only override when explicit.

delete_entities

ChatGPT
Delete one or more observations, insights, solutions or documents. Reos offers no way to restore deleted items, so treat the deletion as permanent and do not tell the user it can be undone or recovered. Only call it for items the user has explicitly agreed to delete in this conversation, and pass confirmedUnselected: true to record that confirmation.

edit_entity

ChatGPT
Edit one observation, insight or solution. Three kinds of change, which can be combined in one call: (1) rewrite: set content (and optionally title for insights and solutions) to replace the text; (2) evidence, for insights only: linkSupportingObservationIds or linkContradictingObservationIds to attach observations as supporting or contradicting evidence, unlinkObservationIds to detach them; a link list also changes the stance of an observation that is already linked; (3) tags: addTagIds and removeTagIds on any entity type, with tag ids from list_tags. Edits one item per call.

fetch

ChatGPT
Read one research item in full by the id a search result carried - the complete observation, insight, solution, document, uploaded resource, or persona, not the snippet. Ids look like insight:<uuid>; pass one back exactly as search returned it.

get_flow_run_results

ChatGPT
Read the entities a completed flow run produced. Call get_flow_run_status first and only fetch results once status is 'completed'. outputType selects what to read - 'observations', 'insights', 'solutions', 'documents', or 'reports' - and should match the run's output type.

get_flow_run_status

ChatGPT
Get the current status of a run started with start_flow_run. Pass exactly one of the ids it returned: flowRunId, batchRunId or batchJobId. Poll until status is 'completed' (or 'failed' / 'cancelled'), waiting a few seconds between polls, before reading results. Returns the status, and what went wrong if it failed.

get_frame

ChatGPT
Extract a still image from a video / screen-recording resource at a timecode and return it as an inline image with the resolved timecode. Pair it with get_transcript segment timecodes to grab the exact moment you want to reference. Pass resourceId and timestampMs (milliseconds from the start). Set describe: true to also get a one-line AI description of what's on screen. Frames are cached, so repeat calls for the same moment are cheap.

get_linked_observations

ChatGPT
List observations currently linked to an insight as evidence, with the stance of each link (supporting or contradicting). Use when the user asks what evidence backs an insight, what counters it, which observations support or contradict it, or where a finding came from. Prefer this over search_data when the user is asking about an insight that's already in the selection — the linked evidence is authoritative. Also use it before changing an evidence link's classification, so you know which observations are currently supporting vs contradicting.

get_observations

ChatGPT
Read the complete text of every observation in a project, page by page, with each observation's participants and source raw data. Unlike search_data (semantic, at most 20 results) and list_entities (short previews), it returns full text and pages through the whole set with a cursor. Call it without a cursor first, then again with the returned cursor until it reports the end. On very large projects, read one participant at a time with participantId. For a count use list_entities; for one participant's coverage get_participant_observations is lighter.

get_participant_observations

ChatGPT
Return exact participant coverage for a project. With participantId or participantName: the exact number of that participant's observations, a sample of them, and which persona the participant's record is linked to, if any. Without either: every participant on the project's raw data with their exact observation count, the total number of participants, and any interviews with no participant linked. Use it for questions such as 'what do we know about this person?', 'how many observations do we have for them?' or 'how many participants do we have?'. The counts are exact whatever the sample size; search_data is semantic and capped at 20 results, so it cannot answer these.

get_project_status

ChatGPT
Return counts of what a project contains: research questions, raw data (resources), observations, insights, solutions, documents, reports and channels. Use it to decide what to do next, for example before start_flow_run, and to check that a stage has finished. researchQuestionCandidates counts questions inferred from the project's data that the user has not confirmed; they are not part of the project's research questions.

get_transcript

ChatGPT
Fetch the verbatim transcript of a recording/interview/screen-recording resource as sentence-level segments with start/end timecodes (in seconds), speaker, and text - plus a processing status. Pass resourceId (get it from list_entities with entity_type 'resource', or from search results). Use the per-segment timecodes to decide where to pull a still with get_frame. status is one of: 'ready' (segments returned), 'processing' (still transcribing - try again shortly), 'no_transcript' (none exists), 'unavailable' (temporarily unreadable).

list_comments

ChatGPT
List the inline, timecoded comments / timeline markers on a resource. Returns each marker with its timecode (seconds), text, author, and source ('resource' = a teammate's note, 'live' = a marker dropped during a hosted interview). Live markers also carry markers flags (tag, isGreatQuote, isKeyMoment); these flags are how Reos records reactions to a moment. Pass resourceId.

list_documents

ChatGPT
List the documents in a project: id, title, type, visibility, status and its path in the Reos app. Pass titleContains for a case-insensitive match on the title, which finds a named document more reliably than the semantic search_data. Use it before create_document when the user names a document, to avoid creating a duplicate. Returns non-deleted documents only.

list_entities

ChatGPT
List a project's (or the organisation's) research data with an exact total: resources (raw data such as interviews, recordings, uploads and data sets), observations, insights, solutions, reports, personas and super_insights. Returns the exact count of matching items plus a page of them, newest first. Use it to answer 'how many X do I have?' or 'list my interviews / insights'; search_data is semantic, returns at most 20 results and is not a count. Results are paginated: while truncated is true, call again with the returned nextCursor and the same arguments. personas and super_insights are organisation-wide and need no project. For documents use list_documents; for an overview of every stage use get_project_status; to read every observation in full use get_observations. If a nameContains lookup finds nothing in the given project, it also reports matches in your other accessible projects.

list_flows

ChatGPT
List the analysis flows available in this organisation, built-in and custom. Optional outputType filter: 'observations', 'insights', 'solutions', 'documents', 'super_insights' or 'questions'. Use it before start_flow_run when you need a specific flow or want to know what the organisation has set up.

list_organizations

ChatGPT
List the organisations this connection can access (the ones chosen when it was connected). Returns each org's id (pass it as the optional orgId argument on any other tool to work in that org), slug, name, and your role there. The org flagged isCurrent: true is the one used when you omit orgId.

list_projects

ChatGPT
List the user's projects in this organization, with id, name, and short description. Returns the EXACT total count of accessible projects (authoritative — quote it verbatim) plus the list, newest first. The default limit covers whole orgs, so the first call normally returns every project; if truncated is true, more exist than shown — call again with the returned nextCursor until every project is listed. Useful when the user asks 'what projects do I have', to pick one to work on, or to establish the full project set before cross-project work.

list_tags

ChatGPT
List the org's available tags (id, name, description, category, allowed entity types) so you can resolve a user-spoken tag name to its UUID before calling edit_entity with addTagIds/removeTagIds. Pass entityType (observation/insight/solution) to narrow to tags that are valid for that entity type — otherwise returns the full catalogue.

search_data

ChatGPT
Search the organization's research data. Use this to find interviews, observations, insights, documents, and other research content. Call this tool when you need to find specific information to answer the user's question.

start_flow_run

ChatGPT
Start an asynchronous flow run to produce observations, insights, solutions, or documents for a project. For observations/insights/solutions this runs the project's pipeline stage (auto-selecting the flow and pending-only inputs, with batch/cluster processing for large sets). For documents/super_insights/questions it runs over ALL live items of the matching input type unless you pass explicit inputIds. Written reports do NOT come from flow runs - they are built in the report builder (Act > Reports). Returns a flowRunId immediately (a batch returns a batchRunId or batchJobId instead) - poll get_flow_run_status with it until completed, then read the results. Clarify steps are skipped automatically for headless runs.

add_text_resource

Claude

add_url_resource

Claude

create_document

Claude

create_project

Claude

delete_entities

Claude

edit_entity

Claude

fetch

Claude

get_flow_run_results

Claude

get_flow_run_status

Claude

get_frame

Claude

get_linked_observations

Claude

get_observations

Claude

get_participant_observations

Claude

get_project_status

Claude

get_transcript

Claude

list_comments

Claude

list_documents

Claude

list_entities

Claude

list_flows

Claude

list_organizations

Claude

list_projects

Claude

list_tags

Claude

search_data

Claude

start_flow_run

Claude

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/reos"><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/reos)