Fellow logo — MCP server on Gumloop

Fellow MCP Server

Connect to the Fellow MCP server to search meeting recordings, read transcripts, and pull meeting notes using AI agents on Gumloop, Claude, or Cursor.

Talk to Sales

Try Fellow now

Type what you want done. Sign in and run it live with an AI agent.

|

Fellow logoFellow
Gradient

Installation

Get StartedGet Started
1

Create a Gumloop Account

To use this MCP, you need a Gumloop account. If you don't have one yet, you can create one for free.

2

Copy Your Server URL

Copy your MCP server URL and add it to your client. You'll be prompted to authorize on first use.

Tools (5)

  • Get Me

    Get information about the authenticated user and their workspace

  • List Recordings

    List recordings from your Fellow workspace with optional filtering and pagination. Supports including expensive fields like transcripts.

  • Get Recording

    Retrieve a specific recording by its ID, with optional transcript inclusion

  • List Notes

    List notes from your Fellow workspace with optional filtering and pagination. Supports including expensive fields like content and attendees.

  • Get Note

    Retrieve a specific note by its ID, with optional content and attendees inclusion

What is Fellow MCP?

The Fellow MCP server gives AI agents read access to your Fellow meeting data. That means agents can identify your connected workspace, list and filter meeting recordings, open a single recording to read its speaker-attributed transcript, browse and filter meeting notes, and pull a note’s full Markdown content along with its attendee list. It works across the recordings and notes in your Fellow workspace, and it links the two together, so an agent can move from a recording to its matching note (or back) on its own.

If you spend time scrubbing through recordings to find one decision, copying transcript snippets into a doc, or rebuilding a weekly recap of what happened across every meeting, an AI agent can take that off your plate. Describe what you need, and your AI agent will pull the right recordings, transcripts, and notes for you.

MCP stands for Model Context Protocol. It’s an open standard that gives AI agents a way to connect to external tools and services. Instead of writing code against the Fellow API, setting the X-API-KEY header on every call, handling pagination, and parsing JSON yourself, you add your Fellow API key and workspace subdomain to Gumloop once. After that, you can read your meeting history just by chatting with your AI agent.

Related MCP servers

What you can do with Fellow MCP on Gumloop

  • Find meeting recordings fast

    List recordings and narrow them by title, date range, event, or channel. The server paginates for you, so a single request can return up to the limit you set across many pages.

  • Read full recording transcripts

    Open any recording to pull its speaker-attributed transcript. Each segment carries the speaker name, start and end times, the spoken text, and a language code, ready for an agent to summarize or search.

  • Open a single recording in detail

    Retrieve one recording by ID with its metadata (title, timestamps, event GUID, call URL, and linked note ID), with the transcript included on request.

  • Browse and filter meeting notes

    List notes with the same filters as recordings (title, date range, event, channel), so an agent can gather every note from a quarter, a project, or a single recurring meeting.

  • Pull note content as Markdown

    Read a note’s full body in Markdown plus its attendee list. The clean Markdown drops straight into summaries, search, or a downstream doc.

  • Cross-reference recordings and notes

    Recordings carry a linked note ID and notes carry linked recording IDs, so an agent can jump from a transcript to the written note for the same meeting.

  • Confirm the connected workspace

    Check which user and Fellow workspace the agent is connected to before it reads anything, useful when you run agents across more than one account.

How to connect the Gumloop Fellow MCP Server

  1. 1

    Create a free Gumloop account

    Sign up at gumloop.com. No credit card required.

  2. 2

    Add the Fellow MCP server

    Copy your MCP server URL from Gumloop and add it to your preferred client (Claude, Cursor, or Gumloop workflows). You'll authorize on first use.

  3. 3

    Start using Fellow in your AI workflows

    That's it. Your AI agent can now search recordings, read transcripts, and pull meeting notes for you. Use it inside a Gumloop automation, in Claude Desktop, or in Cursor.

Fellow MCP use cases

Catch-up briefs for managers who missed the meeting

A manager who skipped a call asks an agent what happened. The agent lists the recording for that meeting, pulls the transcript, and reads the linked note, then hands back a short summary of decisions and open questions. No scrubbing through a recording to find the one minute that mattered.

Pre-read packets for executive assistants and chiefs of staff

Before a leadership sync, an EA has an agent gather every recording and note from the past two weeks tied to a project channel. The agent reads the transcripts and Markdown notes, then drafts a one-page brief so the exec walks in prepared.

Customer call recaps for CS and sales teams

After a customer call, a customer-facing team has an agent pull the recording transcript and the meeting note, then post a clean recap to Slack or write it into a CRM record. The team keeps a shared memory of every account conversation without anyone retyping it.

Research synthesis for product and UX teams

A product team runs a round of discovery calls and wants the themes. An agent lists the recordings for that date range, pulls each transcript, and pulls the matching notes, then groups the findings into a single research doc for the team to review.

Weekly meeting digests for operations and PMO leads

An operations lead wants a Friday digest of the week’s meetings. An agent filters notes and recordings by date range and channel, reads the content, and assembles a roll-up of what was discussed across teams, so leadership sees the whole week in one place.

Why use Gumloop for Fellow MCP

  • Add your key once, not on every call

    Fellow uses API key authentication, so you generate a key, pair it with your workspace subdomain, and add both to Gumloop one time. Gumloop stores them securely and sets the auth header on every request, so you skip env vars, token juggling, and code.

  • Works with multiple MCP clients

    Use the Fellow MCP server endpoint in Claude Desktop, Cursor, or directly inside Gumloop agents. Same server URL, works with any MCP client.

  • Chain Fellow with 100+ other integrations

    Combine Fellow with Slack, Google Tasks, Notion, and other MCP tools in a single AI agent. An agent can pull a transcript from Fellow, summarize it, post the recap to Slack, and write the action points into Google Tasks, all in one run.

  • Enterprise-grade and scalable

    Built for teams, with role-based access and dedicated support for Pro users. For details on Gumloop’s security practices, see trust.gumloop.com.

  • Pricing includes a free plan

    You can test the Fellow MCP integration on Gumloop’s free tier before committing. Paid plans start at $37/month with higher usage limits and additional features.

Frequently asked questions

Ship Fellow agents in minutes

Connect any AI agent to 100+ MCP servers, fully hosted, zero setup.
Talk to Sales
Gradient