Can my agent retrieve the summary of a specific meeting from Fathom?

Yes. Use the 'get_summary' tool. Provide the meeting ID, and the agent will return the AI-distilled context, including key discussion points and decisions made during the call natively.

How do I extract action items from a call via chat?

Use the 'get_action_items' tool. Your agent will parse the AI-identified tasks, returning assigned owners and descriptions, making it easy to automate your follow-up workflows.

Can I search for meetings where a specific keyword was mentioned through the agent?

Absolutely. Use the 'search_meetings' tool. Provide your query, and the agent will search through titles, transcripts, and summaries to find matching meetings across your entire Fathom history.

Fathom MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Fathom
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Fathom through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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 Fathom "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Fathom?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 Fathom MCP Server

Connect your Fathom.video account to any AI agent and take full control of your meeting intelligence and automated note-taking through natural conversation.

Pydantic AI validates every Fathom 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 Orchestration — List recent meetings and search across your entire recording history to retrieve titles, dates, and participant metadata natively
AI Transcription — Retrieve full speaker-attributed transcripts with timestamps to review exact discussions and verbal commitments limitlessly
Contextual Summarization — Get AI-generated summaries distilling key discussion points, decisions, and overall meeting context into a concise format
Action Item Tracking — Extract AI-identified tasks with assigned owners and due dates to automate post-meeting follow-up workflows
Recording Management — Access video and audio recording URLs for immediate streaming or download bypassing the web interface
Attendee Auditing — List all meeting participants including join/leave times and speaking duration to verify engagement levels synchronously
Team Intelligence — Access meetings shared with your Fathom team to monitor cross-functional discussions and organizational knowledge securely
Highlight Navigation — Retrieve specific moments flagged as important during calls to focus on critical insights without reviewing entire recordings

The Fathom 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 Fathom to Pydantic AI via MCP

Follow these steps to integrate the Fathom 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 Fathom with type-safe schemas

Why Use Pydantic AI with the Fathom MCP Server

Pydantic AI provides unique advantages when paired with Fathom 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 Fathom integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Fathom connection logic from agent behavior for testable, maintainable code

Fathom + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Fathom MCP Server delivers measurable value.

Type-safe data pipelines: query Fathom with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Fathom tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Fathom and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Fathom responses and write comprehensive agent tests

Fathom MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Fathom to Pydantic AI via MCP:

get_action_items

Get AI-identified action items for a meeting

get_attendees

Get the list of participants for a meeting

get_highlights

Get important moments flagged in a meeting

get_me

Get current API token user profile

get_meeting

Get details for a specific Fathom meeting

get_recording

Get the recording URLs for a meeting

get_summary

Get the AI-generated summary for a meeting

get_team_meetings

List meetings shared with your team

get_transcript

Get the full transcript for a meeting

get_webhooks

List configured webhooks

list_meetings

List all Fathom meetings

search_meetings

Search for meetings by keyword

Example Prompts for Fathom in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Fathom immediately.

"Show me the summary and action items for my last meeting"

"Search my meetings for mentions of 'pricing strategy'"

"Get the transcript for meeting 'abc-123'"

Troubleshooting Fathom MCP Server with Pydantic AI

Common issues when connecting Fathom to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Fathom + Pydantic AI FAQ

Common questions about integrating Fathom MCP Server with Pydantic AI.

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 Fathom MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.