MCP Server

Topicflow runs a hosted Model Context Protocol server that lets AI assistants like Claude, Cursor, ChatGPT, and any other MCP-compatible client read your Topicflow workspace and draft updates on your behalf — with explicit confirmation before anything is written.

Server URL

https://app.topicflow.com/mcp

The endpoint speaks streamable HTTP MCP and is protected by OAuth 2.1 with PKCE. The first time your client connects you will be redirected to Topicflow to sign in and approve access. No API keys or static tokens to manage.

Connecting a client

Most MCP clients accept a JSON config block. Paste this into your client’s MCP server settings:

{
  "mcpServers": {
    "topicflow": {
      "type": "http",
      "url": "https://app.topicflow.com/mcp"
    }
  }
}

Claude Desktop and Claude Code

Add the server in Settings → Connectors → Add custom connector (Claude Desktop) or run claude mcp add --transport http topicflow https://app.topicflow.com/mcp (Claude Code). Claude will open a browser window for the Topicflow sign-in.

Cursor

Settings → MCP → Add new MCP server, then paste the JSON config above. Cursor handles the OAuth flow automatically.

ChatGPT

In a ChatGPT workspace that supports custom connectors, add a new connector with the URL above and choose OAuth as the auth method. ChatGPT will discover the Topicflow authorization server and prompt you to sign in.

Other clients

Any client that supports MCP over streamable HTTP with OAuth 2.1 dynamic client registration will work. Point it at the URL above — discovery and registration happen automatically.

OAuth scopes

When you approve a connection, the client requests one or more of these scopes. Each area of Topicflow has its own read and write scope, so a client can be given access to your goals without also being given your private notes.

Scope	What it allows
`mcp`	Call MCP tools against your Topicflow workspace
`profile:read`	Read your name, email, team membership, and how your organization is configured
`external-events:read`	Read connected work activity — commits, PRs, tickets, deals
`meetings:read:self` / `meetings:write:self`	Read your meetings; add and edit topics and notes
`goals:read:self` / `goals:write:self`	Read goals and check-in history; create and update goals and check-ins
`feedback:read` / `feedback:write`	Read feedback you can see; draft and edit feedback
`recognitions:read` / `recognitions:write`	Read recognition; draft and edit recognition
`private-notes:read` / `private-notes:write`	Read your own private notes; write and delete them
`reviews:read` / `reviews:write`	Read reviews, progress, and review cycles; complete and reopen reviews, calibrate, nominate peers, approve and share results, configure draft cycles, and manage running ones
`career:read` / `career:write`	Read your organization’s roles and competencies; set up roles, competencies, and who holds each role
`offline_access`	Refresh access without signing in again

Access is bound to you and your organization. The MCP server only ever returns data you can already see in Topicflow — visibility rules for private feedback, other people’s one-on-ones, and team-scoped goals are enforced exactly as they are in the app.

Available tools

Read tools

Tool	What it returns
`get_user_infos`	Look up people by name, team, or email — including manager, team, and career track
`get_organization_context`	How your organization is configured: the label it uses for each feature, its recognition core values, which features are on, and the month its fiscal year starts
`list_meetings`	Recent meetings filtered by participants, title, one-on-one vs. team, and date range, optionally with a short summary of notes and transcript
`get_meeting_transcript`	The full word-for-word transcript of one meeting, speaker by speaker. Long transcripts come back in pages
`list_goals`	Goals you own, manage, or can see, with state and progress
`list_goal_checkins`	Check-in history for a goal, so an assistant can see what was already reported before writing a new update
`list_feedback`	Feedback you’ve given or received, including requests you’ve made that are still waiting for an answer
`list_recognitions`	Recognition given and received, filterable by core value
`list_private_notes`	Your own private notes about people — never anyone else’s
`query_external_events`	Work activity for a visible user from connected tools (GitHub, Jira, Linear, Salesforce, etc.) over a date range

Reviews have their own set of read tools:

Tool	What it returns
`list_review_programs`	Review cycles you can see, filterable by state
`list_my_review_tasks`	Reviews and self-reviews currently assigned to you
`list_assessments`	Review assessments visible to you, optionally with written answers and ratings for reporting
`get_review_progress`	Your own draft review: the answers saved so far and the next unanswered question
`list_review_program_participants`	Who is enrolled in a cycle
`list_review_program_assignments`	Every review requirement in a cycle, including work that hasn’t started or is blocked
`list_review_program_events`	A cycle’s activity log — notifications and reminders sent, with sent, failed, and skipped counts, plus admin actions
`get_peer_nomination_options`	People eligible to review someone
`get_review_calibration`	Calibration data for one person’s review
`get_review_delivery`	A finished review’s results, what the employee will see, and whether it can be approved or shared
`list_review_program_setup_options`	Question sets, participant scopes, and other options available while configuring a draft cycle
`get_review_program_setup`	The saved configuration of a draft cycle, and anything still missing before it can be published

Write tools

Write tools never commit on the first call. They follow a preview → confirm pattern so the assistant can show you exactly what will be created or changed before anything lands in Topicflow.

Tool	What it does
`create_feedback`	Preview a piece of feedback for a teammate
`create_goal`	Preview a new goal with title and key results
`create_goal_checkin`	Preview a progress update on an existing goal
`create_recognition`	Preview a recognition tied to a core value
`edit_goal`	Preview an update to an existing goal
`edit_feedback`	Preview an edit to a piece of feedback
`edit_recognition`	Preview an edit to a recognition
`create_private_note`	Save a private note about yourself or a direct report
`edit_meeting_topic`	Preview an edit to a meeting topic
`edit_meeting_topic_notes`	Preview an edit to meeting topic notes
`add_meeting_topics`	Preview one or more topics to add to a meeting
`delete_private_note`	Preview deleting one of your own private notes
`confirm_creation`	Commit a previously previewed creation or edit by its pending ID

create_private_note is the one exception to the preview pattern — it saves straight away, because a private note is only ever visible to the person who wrote it. Reviews follow the same pattern:

Tool	What it does
`start_review`	Preview opening or resuming a review assigned to you
`answer_review_question`	Preview saving your answer to one question, or an explicit skip
`submit_review`	Preview the finished review, question by question, before it is submitted
`update_peer_nominations`	Preview the peer reviewers selected for someone
`reopen_review`	Preview reopening a submitted review or survey response so it can be revised
`calibrate_review_answer`	Preview a calibrated rating or comment on a review answer
`complete_review_calibration`	Preview marking a calibration complete
`update_review_delivery`	Preview editing a review’s results, requesting approval, approving, or sharing them with the employee
`send_review_reminder`	Preview a reminder to the people who still owe a step in a running cycle
`change_review_dates`	Preview new kickoff, due, or evaluation-period dates for a cycle
`update_review_participant`	Preview excusing one person from a running cycle, adding them back, or removing them
`configure_review_program_workflow`	Preview a draft cycle’s schedule and which review steps run
`configure_review_program_questions`	Preview the question sets each review type uses
`configure_review_program_participants`	Preview who takes part
`configure_review_program_notifications`	Preview the reminder schedule

Roles and competencies have their own set, used by admins to build a role framework in conversation — optionally starting from a document you already have:

Tool	What it does
`get_role_framework_setup`	Your organization’s saved tracks, roles, competencies, and criteria
`list_role_framework_employees`	Employees and the roles they currently hold
`configure_role_framework_structure`	Preview new tracks, roles, and responsibilities
`configure_role_framework_competencies`	Preview new competencies and their criteria
`configure_role_framework_assignments`	Preview the roles assigned to employees

A typical write flow:

Assistant gathers context with read tools (list_meetings, query_external_events, list_assessments).
Assistant calls a write tool and shows you the preview it returns.
You confirm.
Assistant calls confirm_creation with the pending ID, and the record is created or updated in Topicflow.

If you don’t confirm, nothing is written.

Example prompts

Once connected, you can talk to your assistant the same way you would talk to Topicflow AI inside Topicflow:

“What did Riley ship this sprint? Draft recognition tied to our ‘ship fast’ core value.”
“Summarize my last three one-on-ones with Jordan and suggest topics for tomorrow.”
“Look at my open PRs and draft a goal check-in for my Q2 reliability goal.”
“What feedback have I given in the last month? Is anything missing for my upcoming review?”
“Update my Q3 reliability goal to reflect the progress from last week’s deploy.”
“Walk me through my self-review one question at a time, using my goals and shipped work as a starting point.”
“Which of my team hasn’t submitted their review yet, and were they actually sent the reminder?”
“Analyze the transcript from this morning’s stand-up and list the decisions we made.”

Privacy and limits

The MCP server respects every visibility rule in Topicflow. Private feedback stays private, and you cannot see other people’s one-on-ones or scoped goals through MCP that you couldn’t see in the app.
Write tools always require explicit confirmation through confirm_creation. An assistant cannot create or edit feedback, goals, check-ins, recognition, or review answers silently. The single exception is create_private_note, which writes immediately because the note is only ever visible to you.
Private notes are yours alone. list_private_notes returns only notes you wrote, and never anyone else’s.
You can revoke a connected client at any time from Settings → Integrations → Connected apps. Revoking immediately invalidates the OAuth tokens.
Tokens are short-lived and refreshed automatically by the client. There are no long-lived API keys to rotate.

What’s next

Topicflow AI

Use Topicflow’s built-in AI assistant

Integrations

Connect work tools that feed query_external_events

Roles and permissions

Understand what each user can see

Visibility and privacy

See how visibility rules are enforced

Getting Started

Meetings & Tasks

Goals & Performance

Feedback & Recognition

Surveys

Analytics & AI

Configuration

Server URL

Connecting a client

Claude Desktop and Claude Code

Cursor

ChatGPT

Other clients

OAuth scopes

Available tools

Read tools

Write tools

Example prompts

Privacy and limits

What’s next

Topicflow AI

Integrations

Roles and permissions

Visibility and privacy

​Server URL

​Connecting a client

​Claude Desktop and Claude Code

​Cursor

​ChatGPT

​Other clients

​OAuth scopes

​Available tools

​Read tools

​Write tools

​Example prompts

​Privacy and limits

​What’s next

Topicflow AI

Integrations

Roles and permissions

Visibility and privacy

Server URL

Connecting a client

Claude Desktop and Claude Code

Cursor

ChatGPT

Other clients

OAuth scopes

Available tools

Read tools

Write tools

Example prompts

Privacy and limits

What’s next