How to Use the Fathom MCP in AutoGen

Q: How do AutoGen agents access Fathom meeting data?

You register the Fathom MCP Server tools using the mcpservertools adapter. This exposes tools like gettranscript and getsummary directly to your AssistantAgent constructor.

Q: Can AutoGen agents debate Fathom action items?

Yes. One agent can retrieve items via getactionitems, while another reviews the transcript using gettranscript. They converse to verify if the action items accurately reflect the conversation.

Q: How does AutoGen use Fathom webhooks?

Your system can listen to getwebhooks. When a new meeting event occurs, it triggers an AutoGen conversation where agents analyze the new getsummary and coordinate follow-ups.

Q: Can I search past recordings using AutoGen?

Yes. An agent can call searchmeetings with specific keywords to find past recordings, then call getrecording to retrieve the video URLs for further analysis.

Let AutoGen agents debate and coordinate follow-up tasks using your Fathom meeting records.

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 AutoGen

Create your Vinkius account to connect Fathom to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent deliberation on Fathom transcripts

The Fathom MCP Server enables multiple AutoGen agents to collaborate on analyzing meeting discussions. A product manager agent can call `get_transcript` to review feature requests, while a quality assurance agent calls `get_highlights` to identify potential bugs mentioned by the client. These agents then debate the priority of each issue inside your conversation framework. By sharing the raw transcript data, they reach a consensus on what needs immediate attention before calling any external APIs to update your tracker.

Coordinate tasks using this MCP Server

This MCP Server provides tools like `get_action_items` and `get_summary` that separate AutoGen agents use to assign tasks. An AutoGen coordinator agent pulls the summary using `get_summary`, while a task agent parses the action items from `get_action_items` to match them with specific team members. If there is a dispute about who is responsible for a task, the coordinator agent calls `get_attendees` to verify who was present. The agents resolve the ownership conflict dynamically in their chat log before finalizing the task list.

Automate team syncs with AutoGen

The Fathom MCP Server helps your AutoGen agents monitor team-wide progress using `get_team_meetings` and `list_meetings`. A manager agent can search for recent syncs, retrieve the metadata via `get_meeting`, and share updates with other agents in the conversation. By monitoring `get_webhooks`, your AutoGen agents can trigger these sync reviews automatically whenever a new recording is processed. The agents discuss the highlights and draft a unified team update without requiring manual oversight.

Setup guide

Set up Fathom MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Fathom tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Fathom_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Fathom data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Fathom_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Fathom data")
    print(result.messages[-1].content)

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 AutoGen

You register the Fathom MCP Server tools using the mcp_server_tools adapter. This exposes tools like `get_transcript` and `get_summary` directly to your AssistantAgent constructor.

Yes. One agent can retrieve items via `get_action_items`, while another reviews the transcript using `get_transcript`. They converse to verify if the action items accurately reflect the conversation.

Your system can listen to `get_webhooks`. When a new meeting event occurs, it triggers an AutoGen conversation where agents analyze the new `get_summary` and coordinate follow-ups.

Yes. An agent can call `search_meetings` with specific keywords to find past recordings, then call `get_recording` to retrieve the video URLs for further analysis.

Yes. Your meeting recordings, attendee lists, and transcripts retrieved via `get_recording` and `get_attendees` are transmitted over TLS directly to your local runtime. Vinkius executes the server in a zero-trust sandbox, preventing any exposure of your meeting metadata to external networks.

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