How to Use the Fathom MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK hand off Fathom summaries to other agents?

Yes. One agent calls getsummary to extract meeting notes, then hands off that structured text to a specialized CRM-writing agent. The SDK handles these transitions cleanly while keeping a complete trace of the data flow.

Q: How does OpenAI Agents SDK handle API limits when calling Fathom?

You should cache the tool list using the cacheToolsList=True parameter during configuration. This prevents redundant schema lookups and keeps your agent fast and responsive.

Q: Can I retrieve attendee details for a specific call?

Use getattendees to get the participant list for any meeting. This allows your agent to cross-reference names with your CRM contacts.

Feed real-time meeting intelligence directly to your OpenAI Agents SDK pipeline with zero manual data entry.

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 OpenAI Agents SDK

Create your Vinkius account to connect Fathom to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pull action items directly into OpenAI Agents SDK

`get_action_items` extracts concrete tasks from your calls so your OpenAI Agents SDK agent assigns them immediately. You get raw, structured decisions without digging through transcripts. The agent reads the generated list, validates it against your safety guardrails, and passes the tasks to your task manager. Because this MCP Server runs in a secure V8 sandbox, your meeting data stays isolated.

Feed raw transcripts to specialized OpenAI agents

`get_transcript` pulls the complete verbal record of any call into your multi-agent architecture. Specialized agents parse complex technical discussions or customer feedback without manual exports. Use `get_highlights` alongside it to isolate the exact moments where customers agreed to terms or raised objections. The OpenAI dashboard traces every single tool call, letting you audit how your agent processes this sensitive conversational data.

Search Fathom archives via MCP

`search_meetings` lets your agent query your entire call history using natural language to find specific historical contexts. You don't need to build a custom vector database for your meeting notes. Combine this with `get_summary` to quickly generate context sheets before active sales calls. Your agent handles the lookup, retrieves the key points, and preps your team automatically.

Setup guide

Set up Fathom MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Fathom tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Fathom tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Fathom tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Fathom Agent",
            instructions="You have access to Fathom tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package using pip, then initialize the MCP client with your Vinkius endpoint. Pass the server instance directly to the Agent constructor, and the SDK auto-discovers all 12 tools instantly.

Yes. One agent calls `get_summary` to extract meeting notes, then hands off that structured text to a specialized CRM-writing agent. The SDK handles these transitions cleanly while keeping a complete trace of the data flow.

You should cache the tool list using the `cacheToolsList=True` parameter during configuration. This prevents redundant schema lookups and keeps your agent fast and responsive.

Use `get_attendees` to get the participant list for any meeting. This allows your agent to cross-reference names with your CRM contacts.

Yes. Vinkius runs the server in an ephemeral, zero-trust V8 isolate sandbox. Your meeting transcripts, summaries, and action items are never stored on the platform, and authentication is managed via a single secure token.

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