How to Use the Fathom MCP in LlamaIndex

Q: Can LlamaIndex search through Fathom summaries semantically?

Yes. By calling getsummary or searchmeetings, LlamaIndex retrieves the text and indexes it. You can then run semantic queries to find patterns across dozens of different meeting summaries.

Q: How does LlamaIndex handle Fathom action items?

The agent calls getactionitems to retrieve the structured list of tasks. LlamaIndex can then index these tasks separately, allowing you to search for pending action items by owner or topic.

Index your Fathom meeting summaries and transcripts directly into LlamaIndex vector stores for RAG.

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 LlamaIndex

Create your Vinkius account to connect Fathom to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Fathom transcripts into LlamaIndex vector stores

The Fathom MCP Server lets your LlamaIndex pipelines ingest raw meeting content to build searchable knowledge bases. Your agent calls `get_transcript` and `get_summary` to pull meeting data, then converts these text blocks into vector embeddings. This prevents your query engine from hallucinating details about past client calls. Instead of relying on static files, LlamaIndex uses this active connection to fetch the latest details via `get_meeting`. The tool output is immediately formatted as Document objects, allowing your RAG application to answer complex questions about user feedback or product decisions discussed in recent calls.

Query meeting highlights with LlamaIndex RAG

This MCP Server exposes tools like `get_highlights` and `get_action_items` that LlamaIndex indexes alongside your standard documents. When a user asks about project blockers, the LlamaIndex query engine searches the vector index and retrieves the exact highlights flagged by `get_highlights` during the call. By using `get_attendees`, LlamaIndex maps specific quotes and action items to the actual participants. This structured context ensures that when you run a semantic search over your meeting history, the agent attributes decisions to the correct team members.

Search and retrieve meeting recordings dynamically

The Fathom MCP Server allows your LlamaIndex agent to locate specific media files using `get_recording` and `search_meetings`. When a query requires verifying a verbal agreement, the agent searches for the relevant meeting and pulls the exact recording URL. You can combine this with `get_team_meetings` to build a shared repository of team conversations. LlamaIndex indexes the metadata of these shared calls, making it easy to retrieve summaries and action items across your entire organization's meeting history.

Setup guide

Set up Fathom MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Fathom MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Fathom tools.",
)
response = await agent.run("List recent Fathom data")

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 LlamaIndex

You use the McpToolSpec to register the Fathom MCP Server tools like `get_transcript`. Your ingestion pipeline calls these tools to pull meeting text, chunks the data, and stores the embeddings in your vector database.

Yes. By calling `get_summary` or `search_meetings`, LlamaIndex retrieves the text and indexes it. You can then run semantic queries to find patterns across dozens of different meeting summaries.

The agent calls `get_action_items` to retrieve the structured list of tasks. LlamaIndex can then index these tasks separately, allowing you to search for pending action items by owner or topic.

Yes. You can restrict the agent's scope by using the allowed_tools filter during setup, or by having the agent query specific subsets using `list_meetings` or `get_team_meetings`.

Your meeting summaries, transcripts, and action items retrieved via `get_summary` and `get_action_items` are processed directly in your local memory space. Vinkius hosts the server in a secure, ephemeral container, ensuring your meeting text is never cached or stored externally.

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