How to Use the Fathom MCP in Cursor

Q: How do I configure the Fathom MCP Server inside Cursor?

Add the server to your /.cursor/mcp.json file under the mcpServers key. Once configured, this MCP connection lets your editor invoke the tools directly from your chat panel.

Q: Can Cursor write code based on my Fathom action items?

Yes, Cursor runs getactionitems to pull your tasks and immediately generates the code required to implement those features.

Q: How does Cursor handle long Fathom transcripts without hitting context limits?

The agent uses getsummary or gethighlights to extract bite-sized pieces of data. This keeps your context window clear of unnecessary conversational filler.

Q: Can I find specific team calls from my editor?

Yes, the agent calls searchmeetings to scan your shared history for specific technical terms. You then pull the exact details using getmeeting.

Generate production code using real Fathom meeting data inside Cursor with this dedicated MCP Server.

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 Cursor

Create your Vinkius account to connect Fathom to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject Real Fathom Meeting Data into Cursor

The `get_action_items` tool lets Cursor fetch actual tasks from your product calls to build your todo list directly in your codebase. You do not have to guess what features to write next because the real requirements are right in your editor. Your agent uses `get_transcript` to analyze user feedback sessions and write test cases that match actual user complaints. This keeps your development cycle grounded in real conversation logs instead of vague specifications.

Automate Documentation with Meeting Summaries

The `get_summary` tool pulls structural outlines of engineering discussions to auto-generate markdown documentation. You update your README or API specs using the exact decisions made during your team syncs. By calling `get_highlights`, Cursor extracts the most critical design decisions from your architectural reviews. This saves you from re-watching hour-long videos just to remember why you chose a specific database schema.

Query Team Meetings and Attendees via Agent Mode

The `get_team_meetings` tool displays shared organization calls so you can track progress across different engineering squads. You map out who attended which design review by running `get_attendees` directly from the terminal panel. This MCP integration uses `get_me` to verify your active session permissions before fetching sensitive internal call logs. You get a secure, direct pipeline to your workspace data without leaving your active project files.

Setup guide

Set up Fathom MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Fathom MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Fathom transactions." If the MCP tools are loaded correctly, Cursor will call the Fathom tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "fathom-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

Add the server to your ~/.cursor/mcp.json file under the mcpServers key. Once configured, this MCP connection lets your editor invoke the tools directly from your chat panel.

Yes, Cursor runs `get_action_items` to pull your tasks and immediately generates the code required to implement those features.

The agent uses `get_summary` or `get_highlights` to extract bite-sized pieces of data. This keeps your context window clear of unnecessary conversational filler.

Yes, the agent calls `search_meetings` to scan your shared history for specific technical terms. You then pull the exact details using `get_meeting`.

Your call transcripts and session details are protected by zero-trust sandboxing that prevents persistent data storage. All API requests use secure, single-token authentication that never exposes your credentials to external LLM training pools.

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