Connect
Optimize
Secure
Fathom MCP Server
for AI Agents
Production-ready Fathom MCP server with extensible actions — plus built-in authentication, security, and optimized execution.
Fathom MCP Server
Built by 
StackOne
StackOne 
Coverage
7 Agent Actions
Create, read, update, and delete across Fathom — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Fathom MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Fathom tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Fathom call.
Tools Discovery →What is the Fathom MCP Server?
A Fathom MCP server lets AI agents read and write Fathom data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Fathom MCP server ships with pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Fathom MCP Tools and Actions
Every action from Fathom's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Meetings
- List Meetings
Retrieve a list of meetings recorded by or shared with the authenticated user
Teams
- List Teams
Retrieve a list of teams accessible to the authenticated user
Team Members
- List Team Members
Retrieve a list of members belonging to teams accessible to the authenticated user
Recording Summarys
- Get Recording Summary
Retrieve the call summary for a meeting recording
Recording Transcripts
- Get Recording Transcript
Retrieve the full transcript for a meeting recording
Webhooks
- Create Webhook
Create a webhook for real-time meeting notifications. At least one of include_transcript, include_crm_matches, include_summary, or include_action_items must be true.
- Delete Webhook
Delete an existing webhook by its ID
Fathom AI Agent Use Cases
Connect your AI agent to Fathom and help your team scale the sales operations they run by hand today.
Post-Demo Follow-Up
Use StackOne to connect your AI agent to your CRM, email, and calendar tools to automate post-demo follow-up.
View → Deal Risk Scoring
Use StackOne to connect your AI agent to your CRM, email, and calendar tools to automate deal risk scoring and pipeline alerts.
View → Outbound Prospecting
Use StackOne to connect your AI agent to your CRM, sales engagement, and messaging tools to automate outbound prospecting.
View →Set Up Your Fathom MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Fathom in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Fathom MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Fathom MCP Server FAQ
Fathom MCP server vs direct API integration — what's the difference?
A Fathom MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Fathom. A Fathom MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Fathom at runtime. StackOne provides both.
How does Fathom authentication work for AI agents?
Fathom authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Fathom account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Fathom MCP tools vulnerable to prompt injection?
Yes — Fathom MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Fathom agent and how do I avoid it?
Context bloat happens when Fathom tool schemas and API responses eat your Fathom agent's memory, preventing it from reasoning effectively. A single Fathom query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Fathom agent can access?
Yes — you can limit which actions your Fathom agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Fathom MCP server?
Yes — you can create custom agent actions for your Fathom MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Fathom's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Fathom MCP server?
Skip a Fathom MCP server if your integration is purely software-to-software — direct Fathom API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Fathom actions at runtime.
What AI frameworks and AI clients does the StackOne Fathom MCP server support?
The StackOne Fathom MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.