Supercharge your AI with Fellow. Manage meeting tasks through conversation.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Fellow MCP connects your AI agent directly to your meeting data. Use it to track action items, review full meeting agendas, and get summaries without opening the Fellow app.
It puts accountability right where you work.
What your AI can do
Check fellow status
Verifies that the connection between your AI client and Fellow is active and working.
Complete action item
Marks a previously created action item as finished when the task is done.
Create action item
Creates a new follow-up task, optionally linking it to a meeting and setting an assignee or due date.
The agent fetches and displays a list of the most recent meeting sessions.
You get the complete details for any single, specific meeting you name.
The agent can create new action items, assign them to people, and set due dates.
You can list all current actions—pending, completed, or archived—to check team accountability.
The agent pulls the full content of a specific set of meeting notes.
Ask an AI about this
Compatible AI Apps
OAuth 2.0 Compatible Gemini Waiting for input…
Fellow: 12 Tools for Project Coordination
These tools allow your agent to read, write, and manage every piece of data in your Fellow workspace, from user lists to completed tasks.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Fellow on VinkiusCheck Fellow Status
Verifies that the connection between your AI client and Fellow is active and working.
Complete Action Item
Marks a previously created action item as finished when the task is done.
Create Action Item
Creates a new follow-up task, optionally linking it to a meeting and setting an...
Get Action Item
Retrieves the specific details for one action item using its unique ID.
Get Meeting
Pulls all detailed information about a single, specified meeting session.
Get Note
Retrieves the full text and content of one specific meeting note set.
Get Stream
Gets the complete schedule and details for a recurring series of meetings.
List Action Items
Lists all action items, letting you filter them by status: pending, completed, or...
List Meetings
Retrieves a list of the most recent meetings that occurred in your workspace.
List Notes
Lists meeting notes, optionally filtering them to show only those related to one...
List Streams
Displays all available recurring meeting series in the workspace.
List Users
Lists every user account and their role within the Fellow workspace.
Connect to your AI in seconds. Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token from
cloud.vinkius.com. For OAuth-protected servers, expand Advanced
settings to add credentials.
Start a conversation
Open a new chat. The Fellow integration is available immediately — no restart needed.
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 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ 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
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 connection provides 12 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Juggling Meeting Data Across Three Different Places
Today, if a decision is made during a meeting, someone has to manually write it down. Then, you have to copy that note into the project management tool, and finally, assign it as a task in email. It’s clicking through five different tabs just to get one thing documented.
With this MCP, your agent handles the entire process conversationally. You ask for the action item, and it uses `create_action_item` right away, linking it to the meeting context. The result is a clean task added directly to your workflow.
Get Full Control Over Task Status Using list_action_items
Before this, checking project status meant opening the dedicated dashboard and manually filtering tasks by 'pending' or 'completed'. It was slow and you often missed things.
Now, simply asking your agent to `list_action_items` gives you a filtered view of everything. You see pending items assigned to others, completed work, and what’s due next. The process is immediate.
What your AI can actually do with this
Managing team follow-up shouldn't mean juggling multiple tabs or digging through old documents. This MCP lets you manage your entire collaborative workflow using only natural conversation with any AI client. You can list recent meetings, pull up their full agendas, and get specific notes from past sessions. Better yet, you can tell the agent to create a new task, assign it to someone by email, and set a deadline—all in one go.
When a task is done, you just ask it to mark it complete. Whether you're building complex automation or just need quick answers about last week's decisions, connecting through Vinkius makes all that data available right where your agent lives.
019dd0ef-5e08-7156-854f-0221b934de36 
Here's how it actually works
The bottom line is, your AI client acts as the single pane of glass for everything happening in your meetings and tasks.
First, subscribe to this MCP and enter your Fellow API key in the Vinkius developer settings.
Next, tell your AI agent what you want to do—for example, 'Show me all pending action items from last week.'
The agent sends the request through the MCP, retrieves the structured data from Fellow, and gives you a clean, conversational answer.
Who is this actually for?
Project Managers who hate chasing down follow-up items. Team Leads tired of having to open multiple applications just to review meeting decisions. Anyone whose job depends on keeping team accountability clear.
They use this MCP to track tasks, ensure deliverables are assigned correctly, and pull historical data about project phases.
They rely on it to quickly review meeting notes and action items without having to open the dedicated collaboration platform.
They use this MCP to get structured summaries of decisions made during planning sessions, keeping project documentation current.
What Changes When You Connect
Review full meeting details using get_meeting without leaving your current chat window. You get the entire agenda instantly.
Keep team accountability high by listing all open work items using list_action_items. It helps you see exactly who owns what and when it's due.
Create follow-up tasks immediately after a call using create_action_item, assigning ownership and deadlines right away, so nothing gets forgotten.
Don't hunt for notes. Use list_notes or get_note to pull up structured meeting summaries instantly based on the meeting ID.
When a task is finished, call complete_action_item. It marks the item as done and keeps your project tracking clean.
See it in action
Reviewing Q3 Decisions
A team lead needs to know what was decided in last month's roadmap review. Instead of searching through old emails, they ask the agent to get_meeting details for that specific date and pull up the notes using list_notes. It instantly summarizes the outcome.
Assigning Follow-up Tasks
A project manager just finished a planning session. They ask the agent to create an action item: 'Draft budget proposal.' The agent uses create_action_item, assigning it to finance@corp.com and setting May 1st as the due date.
Checking Project Status
A stakeholder asks, 'What's pending?' The agent runs list_action_items filtered by 'pending'. It provides a list of tasks, including who is responsible and when it's due. No manual dashboard checks needed.
Understanding Recurring Meetings
A new hire needs to know the schedule for the bi-weekly sync. They ask the agent to list_streams, which immediately provides all recurring meeting series and their general schedules.
The honest tradeoffs
Copying raw text notes
Manually copying summaries from a PDF or email into a task list, leading to outdated information.
Use list_notes and then get_note to pull the structured data directly. This ensures you are working with the most recent record.
Forgetting who owns the task
Creating a general 'Follow Up' task without assigning an owner, meaning it sits in limbo until someone remembers.
Always use create_action_item. When you create the item, assign it to a specific user by email and set a clear due date.
Missing context on task status
Just listing tasks without knowing if they were marked complete or are still pending action.
Run list_action_items and filter by 'pending' or 'completed'. This gives you a clear, actionable view of the task lifecycle.
When It Fits, When It Doesn't
Use this MCP if your primary job involves coordinating tasks that result from meetings. You need to check status, create accountability items, or retrieve meeting summaries—that’s it. Don't use this if you just need a simple calendar view of appointments; for that, a pure scheduling tool works better. If all you need is to see who exists in the company, list_users handles that fine, but don't assume every communication platform has task management built in.
Questions you might have
How do I check if the Fellow MCP connection works? +
You run check_fellow_status. This tool simply verifies that your API key is connected and that the system can talk to Fellow. It's a quick test.
Can I find all my recent meetings using list_meetings? +
Yes, running list_meetings gives you a clean list of your most recently held sessions. You then use the meeting name or date to get specific notes later.
How do I make sure an action item is marked as done? +
You call complete_action_item. This tool marks a task—identified by its ID—as finished, updating your official record and keeping the project clear.
What if I want to see all recurring meeting types? +
Use list_streams to get a list of every recurring series. You can then use get_stream to view the specific schedule for any one of those series.
How do I use list_users to understand who is in my workspace? +
The tool returns a comprehensive roster of all members. You get their names, roles, and emails for the entire Fellow workspace.
When calling get_meeting, what specific details does it provide about a meeting? +
It gives you full context beyond just the title. You'll retrieve participant lists, the original agenda, and the overall date/time structure of the event.
When using create_action_item, what is required for a new task? +
You need to specify an assignee by email address and set a due date. You can also optionally link it directly back to the meeting that prompted it.
How do I filter my tasks using list_action_items? +
The function lets you narrow your results by status. Simply specify whether you want to see 'pending', 'completed', or 'archived' items.
Can I create an action item and assign it to a team member? +
Yes! Use create_action_item with the title, assignee email, and optional due date. You can also link it to a specific meeting.
How do I get the notes from a specific meeting? +
Use list_notes with the meeting ID to get all notes linked to that meeting, or get_note with a specific note ID for full content.
Can I mark action items as completed via the AI agent? +
Absolutely. Use complete_action_item with the action item ID to mark it as done.
We've already built the connector for Fellow. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 12 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.