Fellow MCP Server for Pydantic AI 12 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Fellow through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to Fellow "
"(12 tools)."
),
)
result = await agent.run(
"What tools are available in Fellow?"
)
print(result.data)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About 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.
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.
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
The Fellow MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Fellow to Pydantic AI via MCP
Follow these steps to integrate the Fellow MCP Server with Pydantic AI.
Install Pydantic AI
Run pip install pydantic-ai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 12 tools from Fellow with type-safe schemas
Why Use Pydantic AI with the Fellow MCP Server
Pydantic AI provides unique advantages when paired with Fellow through the Model Context Protocol.
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 + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Fellow MCP Server delivers measurable value.
Type-safe data pipelines: query Fellow with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Fellow tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Fellow and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Fellow responses and write comprehensive agent tests
Fellow MCP Tools for Pydantic AI (12)
These 12 tools become available when you connect Fellow to Pydantic AI via MCP:
archive_action_item
Archive an action item, removing it from active views without deleting it
complete_action_item
Use when a task has been finished. Mark an action item as complete
delete_note
Confirm with the user before executing — this cannot be undone. Permanently delete a meeting note by ID
delete_recording
Confirm with the user before executing. Permanently delete a meeting recording by ID
get_action_item
Use to inspect a single task. Retrieve details of a specific action item by ID
get_current_user
Use to verify which account is connected. Retrieve the authenticated Fellow user profile
get_note
Essential for reviewing a specific meeting. Retrieve the full content and metadata of a specific meeting note by ID
get_recording
Use to access a specific recording. Retrieve details of a specific meeting recording
get_transcript
Use for detailed review, compliance documentation, or extracting specific discussion points. Retrieve the full transcript of a meeting recording
list_action_items
Use for cross-meeting task tracking and accountability. List all action items across all meetings
list_notes
Use as the primary entry point to browse all meeting documentation. List all meeting notes in the Fellow workspace
list_recordings
Use to browse all recorded meetings. List all meeting recordings captured by Fellow
Example Prompts for Fellow in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Fellow immediately.
"Show me all my pending action items"
"Get the notes for the meeting 'Product Sync' from last Tuesday"
"List the last 3 meeting recordings"
Troubleshooting Fellow MCP Server with Pydantic AI
Common issues when connecting Fellow to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiFellow + Pydantic AI FAQ
Common questions about integrating Fellow MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
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?
Can I switch LLM providers without changing MCP code?
Connect Fellow with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Fellow to Pydantic AI
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.