How to Use the Fathom MCP in CrewAI

Q: Can my CrewAI agents search through Fathom history?

Yes. Your agents use searchmeetings to find relevant calls by keyword. This allows them to pull historical context into their current task execution.

Use the Fathom MCP server to give your CrewAI agents direct access to meeting transcripts, summaries, and action items.

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 CrewAI

Create your Vinkius account to connect Fathom to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate meeting intelligence in CrewAI

Your agents can now pull raw data from every session without manual copy-pasting. Use `list_meetings` and `search_meetings` to locate specific conversations, then feed the content into your agents for immediate processing. Once you have the meeting ID, use `get_transcript` or `get_summary` to provide your agents with the context they need to execute tasks. This keeps your multi-agent workflow grounded in actual client discussions.

Sync action items across your crew

Stop letting tasks fall through the cracks between agent handoffs. Trigger `get_action_items` to extract specific commitments made during a call and pass them directly to your execution agents. This creates a closed-loop system where your research agents identify needs and your action agents draft the follow-ups. You get a clear audit trail of who promised what, all managed by your autonomous crew.

Monitor team collaboration with an MCP Server

Keep your agents updated on current team progress by using `get_team_meetings` to poll for recent activity. It allows your monitoring agents to stay in the loop on all shared discussions. Combine this with `get_highlights` to filter out the noise and focus your agents on the critical moments of a conversation. It ensures your agents respond only to the most relevant parts of the meeting.

Setup guide

Set up Fathom MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Fathom tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Fathom Analyst",
    goal="Access and analyze Fathom data via MCP.",
    backstory="Expert analyst with direct Fathom access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Fathom transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Fathom Analyst",
        goal="Access and analyze Fathom data via MCP.",
        backstory="Expert analyst with direct Fathom access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Fathom transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You simply pass the Fathom MCP server URL into your Agent configuration. Once added to the mcps array, your agents can call any of the 12 available tools directly.

Yes. Your agents use `search_meetings` to find relevant calls by keyword. This allows them to pull historical context into their current task execution.

It does. You can set up a CrewAI process that polls for new meetings and uses `get_summary` to start a new research task automatically.

The MCP server returns a standard error message. Your agent can then catch this, log the failure, and try a different query or notify you.

Your data remains within your controlled environment. The Fathom MCP server only retrieves meeting transcripts and action items when your agent explicitly requests them.

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