Fellow MCP. Track every decision, task, and meeting detail in one chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Fellow manages all your meeting notes, agendas, and follow-up tasks through your AI client. List all meeting notes, track action items across projects, and retrieve transcripts and recordings—all in one conversation.
Get full control over meeting knowledge and accountability.
What your AI agents can do
Archive action item
Removes a task from active views without actually deleting the task.
Complete action item
Marks a specific task as finished.
Delete note
Permanently deletes a meeting note when you confirm the action.
Retrieves a list of every meeting note in your Fellow workspace.
Pulls the full content and metadata for a single meeting note using its ID.
Generates a list of every task across all your meetings for cross-project tracking.
Retrieves all details for one specific task using its ID.
Lists all recorded meetings and retrieves details for a specific recording.
Pulls the full, time-stamped transcript from a recorded meeting.
Marks an action item as complete, archives it, or allows permanent deletion of notes and recordings.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Fellow MCP Server: 12 Tools for Meeting & Task Management
Use these tools to list, retrieve, and modify all meeting notes, recordings, and action items within your Fellow workspace.
019d7598archive action item
Removes a task from active views without actually deleting the task.
019d7598complete action item
Marks a specific task as finished.
019d7598delete note
Permanently deletes a meeting note when you confirm the action.
019d7598delete recording
Permanently deletes a meeting recording when you confirm the action.
019d7598get action item
Retrieves all details for a specific task using its ID.
019d7598get current user
Retrieves the profile details of the authenticated user connected to the service.
019d7598get note
Retrieves the full content and metadata of a specific meeting note by ID.
019d7598get recording
Retrieves details about a specific meeting recording.
019d7598get transcript
Retrieves the full transcript of a meeting recording for review.
019d7598list action items
Lists every action item across all meetings to track accountability.
019d7598list notes
Lists all meeting notes available in the workspace.
019d7598list recordings
Lists all recorded meetings captured by Fellow.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Fellow, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Fellow keeps track of all your meeting notes, agendas, and follow-up tasks through your AI client. You'll list all meeting notes, track action items across projects, and pull transcripts and recordings—all in one conversation. You get full control over meeting knowledge and accountability.
- Notes and Tasks: You can list every meeting note in your workspace, or pull the full content and metadata for a specific note using its ID. You'll list every action item across all meetings to track accountability, and you can get all the details for one specific task using its ID. You can mark an action item as complete, or you can archive it, and you'll even delete a note or a recording permanently if you confirm it.
- Recordings and Transcripts: You can list all recorded meetings captured by Fellow, and you can pull the details for a specific recording. You'll get the full, time-stamped transcript from any recorded meeting. You can also delete a recording permanently.
- User Context: You can get the profile details of the authenticated user connected to the service.
How Fellow MCP Works
- 1 Subscribe to the Fellow MCP Server and provide your API key.
- 2 Your AI client uses the server's tools to interact with Fellow data (e.g., listing notes, getting action items).
- 3 The agent executes the tool call, retrieving structured data and presenting the results to you in the chat.
The bottom line is, your AI client handles the API calls and presents the structured data, so you just talk to it.
Who Is Fellow MCP For?
Product Managers who need to audit collaborative agendas across weeks. Operations staff who track cross-functional accountability. Managers who hate manually compiling meeting reports. Anyone whose job requires remembering decisions made in a meeting that happened last quarter.
Searches across multiple meeting transcripts to find every mention of a specific feature or decision point.
Checks the status of cross-meeting tasks, verifying assignments and due dates without opening multiple project dashboards.
Gathers all documentation for a stakeholder meeting—the notes, the recordings, and the final action items—via a single chat prompt.
What Changes When You Connect
- Audit every task across multiple projects. Use
list_action_itemsto track descriptions, assignees, and due dates, solving the problem of siloed task lists. - Find specific discussion points instantly. Running
get_transcriptpulls the full transcript with speaker attribution and timestamps, letting you search complex discussions. - Manage the entire meeting lifecycle. Use
list_notesandget_noteto see all agendas and decisions, and then usecomplete_action_itemto mark tasks as done. - Control your data security. Use
delete_noteordelete_recordingto permanently vaporize records when required by compliance. - Streamline task management. You can use
list_action_itemsto pull a list, then useget_action_itemto inspect a single task's details. - Keep context on the user.
get_current_userverifies the authenticated profile, ensuring the agent operates within correct permission boundaries.
Real-World Use Cases
Project Handover Review
A project manager needs to hand off a project and confirm all follow-ups. They ask their agent to list_notes and then list_action_items. The agent compiles a list showing who is responsible for what, and when it's due, allowing the PM to send the project off with confidence.
Compliance Audit
An operations lead needs to find a specific conversation about a data policy from six months ago. They ask the agent to list_recordings and then run get_transcript on the relevant recording. The agent pulls the time-stamped text, allowing the lead to prove the discussion took place.
Post-Meeting Cleanup
A team lead just finished a meeting. Instead of manually updating a Jira ticket, they ask the agent to get_note for the meeting. The agent identifies the action items and runs complete_action_item for the items that were finished right in the chat.
Cross-Departmental Accountability
A PM needs to see if a task assigned in a Marketing meeting was picked up by the Engineering team. They run list_action_items. The agent filters the list by assignee or project, providing a single source of truth for accountability.
The Tradeoffs
Copying meeting data to Notion
The user manually opens the notes, copies the bullet points, and pastes them into a spreadsheet or wiki. They forget to track who was responsible for the action item.
→
Use get_note to retrieve the structured content. Then, use list_action_items to ensure every task is tracked with an owner and due date, keeping the data centralized in Fellow.
Searching keyword-only in recordings
The user tries to recall a specific comment from a presentation by searching keywords in the recording's title. They only get a general sense, not the exact context or speaker.
→
Use list_recordings to find the meeting, then run get_transcript. The agent provides the full transcript with timestamps and speaker names, letting you pinpoint the exact moment.
Treating notes as static documents
The user assumes a meeting note is final and doesn't track changes or task completion status. The notes sit there, unmanaged, and tasks fall through the cracks.
→
Always use list_action_items to view the master list of tasks. When a task is done, use complete_action_item to update the status immediately, keeping your workflow current.
When It Fits, When It Doesn't
Use this if your primary bottleneck is knowledge fragmentation—when decisions and tasks are scattered across different meetings, recordings, and documents. You need a system that connects the 'what was said' (transcripts, notes) with the 'what needs to happen' (action items).
Don't use this if your core need is simple document storage or simple keyword search. If you only need to search for
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Fellow. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 12 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manual meeting summaries are a time sink.
Today, you gather meeting notes from Slack, pull the recording link from Outlook, and then open a separate document to manually compile decisions and next steps. You copy and paste bullet points into a central document, but you lose the context of who agreed to what, or when that decision was made.
With this MCP server, you just ask your agent to process the meeting. It reads the notes, identifies the agenda items, and structures the decisions and tasks. You get a single, clean output that shows exactly what was decided and who owns the follow-up.
Fellow MCP Server: Task Management
You currently have to switch between the notes, the task list, and the calendar just to verify if a task is still active or if the notes are up to date. This takes multiple clicks and cross-referencing.
Now, you ask your agent to `list_action_items`. It pulls every task across every meeting you've ever had, giving you one master list. You see the owner, the due date, and the current status—no jumping between tabs required.
Common Questions About Fellow MCP
How do I check all my pending tasks with the Fellow MCP Server using `list_action_items`? +
Run list_action_items to see a comprehensive list of every task across all your meetings. The agent shows the description, assignee, and due date for every item, letting you quickly audit accountability.
What is the best way to find a specific decision from a meeting note using `get_note`? +
Use get_note and specify the note's ID. The agent retrieves the full, structured content, making it easy to pull out decision metadata and discussion points.
Can I find what was said during a recorded meeting using `get_transcript`? +
Yes. Run get_transcript to get the full, time-stamped transcript. This is better than just searching keywords because you get the speaker attribution and context.
How do I permanently delete a record using `delete_note` or `delete_recording`? +
You must confirm with the agent before running delete_note or delete_recording. These actions are irreversible, so always verify the ID and the data before confirming the deletion.
What is the difference between `get_action_item` and `list_action_items`? +
list_action_items shows you all tasks across all meetings. get_action_item lets you inspect the full details for only one specific task using its ID.
How do I get the full list of meeting notes using `list_notes`? +
Use list_notes to see every meeting note in your workspace. This tool gives you the primary entry point to browse all your meeting documentation.
Can I retrieve the details of a specific meeting recording using `get_recording`? +
Yes, get_recording retrieves the metadata for a specific meeting recording. This includes details like the duration and the date it was captured.
What is the `get_current_user` tool used for? +
The get_current_user tool retrieves your authenticated Fellow profile. You use this to verify which account your AI agent is currently connected to.
Can my agent retrieve the full transcript of a specific meeting recording in Fellow? +
Yes. Use the 'get_transcript' tool. Provide the recording ID, and the agent will return the speaker-attributed text with timestamps, allowing you to review critical discussions or extract insights limitlessly.
How do I mark an action item as complete via chat? +
Use the 'complete_action_item' tool. Provide the item ID. Your agent will update the task status in Fellow and notify the relevant stakeholders, ensuring your project progress is updated synchronously.
Can I see all meeting notes in my workspace through the agent? +
Absolutely. The 'list_notes' tool identifies bounded records inside your workspace, returning note IDs, titles, meeting dates, and participants to help you browse your meeting history natively.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Timeero
Track employee time and mileage with GPS-verified clock-ins that generate accurate timesheets for field service teams.
Freshsales
Manage your CRM pipelines, track leads, and oversee sales deals via AI agents with Freshsales.
Fee Navigator
Analyze merchant statements via Fee Navigator — track potential savings, generate proposals, and manage audits directly through your AI agent.
You might also like
FlightAware
Track global flight status via FlightAware AeroAPI — search flights, monitor airport arrivals and departures, check weather, and access historical flight data from any AI agent.
Dailymotion
Manage video hosting via Dailymotion — upload and publish videos, track view counts, manage playlists, and search public content directly from any AI agent.
YouCanBook.me
Automate scheduling workflows via YouCanBook.me — manage booking pages, appointments, and availability directly from any AI agent.