Grain MCP Server
Connect Grain to your AI agents with the Grain MCP server.
Updated
What is Grain MCP?
The Grain MCP server is a Model Context Protocol server that connects Grain to AI agents and assistants as a set of tools. With it connected, an agent can work with Grain (meeting intelligence — recordings, transcripts, highlights, and notes) directly — instead of you copying data in and out by hand.
It is a remote MCP server that uses OAuth, so you point your client at the server URL, authorize once, and the Grain tools become available to the model.
Connect the Grain MCP server
Connect Grain MCP to Claude Code
- 1
Add the server
Use `claude mcp add` with the Grain MCP server URL (or its `npx` command), following the official docs.
- 2
Authorize
Complete authentication (OAuth) so Claude Code can call the server.
- 3
Verify
Ask Claude to use a Grain tool to confirm the connection is live.
Connect Grain MCP to Cursor
- 1
Open MCP settings
In Cursor, go to Settings → MCP → Add new server.
- 2
Add Grain
Provide the Grain MCP server URL or command and complete authentication.
- 3
Test
Reference Grain from chat to confirm Cursor can reach the tools.
Sample use cases
A sales manager reviews recorded calls after each sprint demo
Grain auto-highlights key moments — objections, pricing questions, and feature requests — saving 30 minutes of manual note-taking per call.
A product team runs a weekly voice-of-customer review
An agent pulls Grain highlights tagged 'feature request' and groups them by theme, surfacing the top three asks for the next sprint.
A customer success agent monitors onboarding calls for risk signals
It flags calls where the customer expressed confusion or dissatisfaction, alerting the CS lead to follow up within 24 hours.
A RevOps analyst builds a weekly coaching digest for the sales team
The agent extracts talk-to-listen ratios and top competitor mentions from Grain recordings, then posts a summary to Slack.
A UX researcher collects usability testing insights
Grain transcripts are searched for hesitation markers and task-failure moments, compiled into a findings report with timestamped clips.
A team lead tracks action items from recurring standup meetings
The agent parses Grain's AI notes for commitments and deadlines, then creates tasks in the project tracker automatically.
A compliance officer audits recorded sales calls for regulatory language
It scans transcripts for required disclosures and flags any calls missing them, generating a weekly compliance report.
Using Grain MCP with Gamut
On Gamut, the Grain MCP server becomes a tool your agents use inside an automated, event-driven workflow — triggered by an event or a schedule, acting through Grain and your other connected MCP servers, with the connection managed by Gamut rather than a local config file.
Frequently asked questions
What is the Grain MCP server?
It is a Model Context Protocol server that exposes Grain to AI agents as tools so they can work with it (meeting intelligence — recordings, transcripts, highlights, and notes).
How do I connect the Grain MCP server?
Point your MCP client (Claude, Cursor, or Gamut) at the Grain MCP server URL and complete authentication (OAuth). See the official documentation for the exact URL and scopes.
Can I use Grain MCP with Gamut?
Yes — Gamut supports the Grain MCP server, so your agents can use it as a tool in automated, triggered workflows.
What types of meetings does Grain record?
Grain records video calls on Zoom, Google Meet, and Microsoft Teams. It captures both audio and video, then generates AI-powered transcripts and highlights.
Can I share Grain highlights with people outside my organization?
Yes. Grain lets you create shareable highlight clips with a link. Recipients do not need a Grain account to view them.
Does Grain support languages other than English?
Grain's transcription supports multiple languages including Spanish, French, German, and Portuguese, though English accuracy is highest.
How does the Grain MCP server connect to AI agents?
The MCP server exposes Grain's recording, transcript, and highlight data as standardized tools that any MCP-compatible AI agent can call — no custom API integration needed.