How to Use the Fathom MCP in Pydantic AI

Q: How do I initialize the Fathom toolset in Pydantic AI?

Import MCPToolset and pass your Vinkius HTTP endpoint. Add this toolset to your agent's toolsets list, and the framework handles schema conversion and validation automatically.

Q: How do I check for new highlights?

Use gethighlights to pull key moments from your calls. Your agent parses these structured objects to generate targeted follow-ups.

Enforce strict runtime validation on Fathom summaries and action items using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fathom MCP to Pydantic AI

Create your Vinkius account to connect Fathom to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Fathom with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate action items with Pydantic AI

`get_action_items` retrieves tasks from your calls and validates them against your strict Python schemas. If the API returns unexpected formatting, Pydantic AI raises a validation error immediately. This guarantees that your agent never pushes malformed tasks to your database. You get clean, predictable data structures every single time.

Type-safe lookups via this MCP Server

`get_meeting` pulls metadata that is instantly parsed into strongly-typed Pydantic models. Your code accesses fields like duration and timestamps without worrying about missing attributes. Combine this with `list_meetings` to build reliable synchronization scripts. The framework catches schema mismatches during development, preventing silent runtime failures in production.

Verify API credentials safely

`get_me` checks the active token profile to ensure your script has the correct permissions before running updates. This prevents unauthorized execution of downstream tools. By verifying the authenticated user first, you keep your workflows secure. The Vinkius MCP platform handles the underlying credential exchange, so your Python code only needs one token.

Setup guide

Set up Fathom MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "fathom-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Fathom tools.",
)

result = await agent.run("List recent Fathom transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Fathom. 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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Fathom now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Fathom MCP in Pydantic AI

Import `MCPToolset` and pass your Vinkius HTTP endpoint. Add this toolset to your agent's `toolsets` list, and the framework handles schema conversion and validation automatically.

The framework raises a validation error at runtime rather than letting corrupt data slip through. This allows you to catch API changes or unexpected payloads before they hit your database.

Yes. The toolset integration supports asynchronous execution, allowing your agent to run `search_meetings` without blocking your application's main thread.

Use `get_highlights` to pull key moments from your calls. Your agent parses these structured objects to generate targeted follow-ups.

Every MCP request runs through an isolated V8 sandbox on Vinkius. Your meeting notes, action items, and transcripts are never written to disk, ensuring strict compliance with enterprise data policies.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript