Bring Meeting Management
to Pydantic AI
Create your Vinkius account to connect Fellow to Pydantic AI and start using all 12 AI tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code. No hosting, no server setup — just connect and start using.
Compatible with every major AI agent and IDE
What is the Fellow MCP Server?
Connect your Fellow.app account to any AI agent and take full control of your meeting management, collaborative agendas, and action item tracking through natural conversation.
What you can do
- Meeting Note Orchestration — List all meeting notes and retrieve full structured content including agenda items, discussion points, and decision metadata natively
- Action Item Auditing — List and filter all tasks across meetings to track descriptions, assignees, and due dates for cross-meeting accountability flawlessly
- Recording Management — Browse meeting recordings and retrieve video/audio details including time-limited download or stream URLs securely
- AI Transcription Retrieval — Fetch full transcripts with speaker attribution and timestamps to review critical discussions or extract specific insights limitlessly
- Task Lifecycle Control — Mark action items as complete or archive them to manage your active workspace and notify relevant stakeholders synchronously
- Identity Oversight — Retrieve the authenticated profile identity including name, email, and workspace contexts to verify permission limits natively
- Data Invalidation — Irreversibly vaporize specific meeting notes or recordings findable by ID to manage your organizational records strictly
How it works
- Subscribe to this server
- Enter your Fellow API Key (found in User Settings > Account > API Tokens)
- Start managing your meeting notes and tasks from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Managers & Team Leads — track team action items and review meeting decisions without manual follow-ups
- Product Managers — audit collaborative agendas and search across meeting transcripts using natural language
- Executive Assistants — manage meeting recordings and organize documentation for stakeholders through the chat interface
- Operations Teams — verify cross-meeting task statuses and monitor organizational knowledge in real-time
Built-in capabilities (12)
Archive an action item, removing it from active views without deleting it
Use when a task has been finished. Mark an action item as complete
Confirm with the user before executing — this cannot be undone. Permanently delete a meeting note by ID
Confirm with the user before executing. Permanently delete a meeting recording by ID
Use to inspect a single task. Retrieve details of a specific action item by ID
Use to verify which account is connected. Retrieve the authenticated Fellow user profile
Essential for reviewing a specific meeting. Retrieve the full content and metadata of a specific meeting note by ID
Use to access a specific recording. Retrieve details of a specific meeting recording
Use for detailed review, compliance documentation, or extracting specific discussion points. Retrieve the full transcript of a meeting recording
Use for cross-meeting task tracking and accountability. List all action items across all meetings
Use as the primary entry point to browse all meeting documentation. List all meeting notes in the Fellow workspace
Use to browse all recorded meetings. List all meeting recordings captured by Fellow
Why Pydantic AI?
Pydantic AI validates every Fellow tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Fellow integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Fellow connection logic from agent behavior for testable, maintainable code
Fellow in Pydantic AI
Why run Fellow with Vinkius?
The Fellow connection runs on our fully managed, secure cloud infrastructure. We handle the hosting, maintenance, and security so you don't have to deal with servers or code. All 12 tools are ready to work instantly without any complex setup.
You stay in complete control of your data. Your AI only accesses the information you approve, keeping your sensitive passwords and private details completely safe. Plus, with automatic optimizations, your AI works faster and more efficiently.

* Every connection is hosted and maintained by Vinkius. We handle the security, updates, and infrastructure so you don't have to write code or manage servers. See our infrastructure
Over 4,000 integrations ready for AI agents
Explore a vast library of pre-built integrations, optimized and ready to deploy.
Connect securely in under 30 seconds
Generate tokens to authenticate and link external services in a single step.
Complete visibility into every agent action
Audit live requests, latency, success rates, and active security compliance policies.
Optimize spending and track token ROI
Analyze real-time token consumption and cost metrics detailed by connection.




Explore our live AI Agents Analytics dashboard to see it all working
This dashboard is included when you connect Fellow using Vinkius. You will never be left in the dark about what your AI agents are doing with your tools.
Fellow and 4,000+ other AI tools. No hosting, no code, ready to use.
Professionals who connect Fellow to Pydantic AI through Vinkius don't need to write code, manage servers, or worry about security. Everything is pre-configured, secure, and runs automatically in the background.
Raw MCP | Vinkius | |
|---|---|---|
| Ready-to-use MCPs | Find and configure each manually | 4,000+ MCPs ready to use |
| Connection Setup | Manual coding & server setup | 1-click instant connection |
| Server Hosting | You host it yourself (needs 24/7 uptime) | 100% hosted & managed by Vinkius |
| Security & Privacy | Stored in plaintext config files | Bank-grade encrypted vault |
| Activity Visibility | Blind execution (no logs or tracking) | Live dashboard with real-time logs |
| Cost Control | Runaway AI token spend risk | Automatic budget limits |
| Revoking Access | Must delete files or code to stop | 1-click disconnect button |
How Vinkius secures
Fellow for Pydantic AI
Every request between Pydantic AI and Fellow is protected by our secure gateway. We automatically keep your sensitive data private, prevent unauthorized access, and let you disconnect instantly at any time.
Frequently asked questions
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.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Fellow MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
Bold
14 toolsAutomate payments via Bold Colombia — manage terminals, process transactions, generate payment links, and track settlements from any AI agent.

Observe.AI
10 toolsAnalyze and evaluate contact center interactions via Observe.AI — track transcripts, QA scores, and coaching directly from your AI agent.

Corsizio
10 toolsEquip your AI agent to manage event registrations, attendees, and payments through the Corsizio API.

Appointlet
10 toolsBring Appointlet scheduling directly into your AI agent — list schedules, track bookings, cancel events, and manage attendees seamlessly.
