fathom-mcp-adapter
Read-only MCP server that exposes Fathom meetings and transcripts as tools for use by skills in the TICKETS workspace.
README
fathom-mcp-adapter
Read-only MCP server that exposes Fathom meetings + transcripts as tools, for use
by /updateP1 (and other skills) in the TICKETS workspace.
This is a private, standalone adapter: its own git repo, its own .env. It is
not part of ia-tooling and does not depend on its stack — it only makes HTTPS
calls out to the Fathom REST API (https://api.fathom.ai/external/v1). It was scaffolded by
cloning the structure of ia-tooling/services/zendesk-mcp-adapter.
Architecture
The adapter is the MCP server. Internally it calls the Fathom REST API directly (just as the Zendesk adapter calls Zendesk's REST API). MCP servers are not chained to one another.
- Auth: per-user API key sent as the
X-Api-Keyheader. The key is scoped to one user (their own meetings + meetings shared to their Team), which provides data isolation between teammates. Rate limit: 60 req/min. - The adapter returns the raw transcript. The who/what/when summary is produced
by the
/updateP1skill, never by a tool here. - There is no title/keyword search in the Fathom API. To find a specific
meeting, list recent meetings (optionally narrowing by
created_after/recorded_by) and let the skill filter by title/date/invitee.
Tools
| Tool | Purpose |
|---|---|
fathom_health |
Config/connectivity check (makes one authenticated call). |
fathom_list_recent_meetings |
List recent meetings, newest first. Filters: created_after, created_before, recorded_by, invitee_domains, meeting_type. |
fathom_get_latest_meeting |
The single most recent meeting (the 90% case for /updateP1). |
fathom_get_transcript |
Raw transcript for a recording_id. |
Each meeting record includes title, recording_id, created_at, url (private,
login-gated) and share_url (team-shareable). For the internal timeline reference
use share_url, never url.
Setup
npm install
cp .env.example .env # then fill in FATHOM_API_KEY
npm test
npm start # speaks MCP over stdio
FATHOM_API_KEY must come from .env (which is git-ignored) — never hardcode it.
Wiring into the TICKETS MCP session
Build the image and add a fathom entry to the TICKETS .mcp.json, alongside
zendesk / vectordb / github. It does not need the ia-tooling_default
network (HTTPS egress only).
docker build -t fathom-mcp-adapter .
// .mcp.json (TICKETS)
{
"mcpServers": {
"fathom": {
"command": "docker",
"args": ["run", "--rm", "-i", "--env-file", "/ABSOLUTE/PATH/TO/.env", "fathom-mcp-adapter"]
}
}
}
Fallback
If the Fathom MCP server is down, /updateP1 falls back to the manual
"paste-me-the-transcript" mode rather than blocking (same pattern as
zendesk/vectordb).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.