PromptHivePromptHive
Granola

Meeting notes and transcripts inside your AI tools

Granola MCP exposes your meeting notes, summaries, and transcripts to Claude, Cursor, and ChatGPT — pull action items and decisions from past calls without copy-paste.

Install MCPVisit website

AI agents can write code. But they don't always know what works. Granola MCP fixes that.

Using Granola, list remaining action items for each person from this week's project meetings.

Cursor

Action items from last standup

Used Granola MCP integration

Results ready. Pulling the strongest patterns for synthesis.

Granola connects your AI agents to real-world references.

Action items from meetings

Pull open action items, owners, and due dates from this week's meetings without rewatching recordings. Granola MCP searches your meeting history and returns structured task lists in plain language. Your agent can group by person, project, or priority. Start a build session knowing exactly what was committed in the last standup.

Action items from meetings preview

Your AI agents can search, reference, and reason about all of it.

Ask anything. Get real results back.

Works withCursorClaude CodeCodexand more.

Action items from last standup

Using Granola, list remaining action items for each person from this week's project meetings.

Quick start

Using Granola MCP, walk me through a first query I can run in Cursor to see what this connector can do.

Research research

Use Granola to research research patterns relevant to my product and summarize the top findings.

Competitive scan

With Granola MCP, compare how 3 leading products handle research and list actionable takeaways.

Feature inspiration

Find inspiration for my next research feature using Granola and suggest 3 directions with examples.

Workflow audit

Audit my current research workflow with Granola MCP and recommend concrete improvements.

Research brief

Build a one-page research brief using Granola for an upcoming launch in the research space.

Summarize findings

Pull data from Granola, summarize the strongest patterns, and propose next steps for my team.

Best practices

What are the best practices teams follow when using Granola MCP inside Cursor or Claude Code?

Micro-decision help

I'm stuck on a research micro-decision — use Granola to surface examples and recommend an approach.

When to reach for Granola MCP

Building from scratch

Your agent analyzes successful patterns and applies them using Granola.

Building from scratch workflow preview

Stuck on a micro-decision

Let agents explore best practices from products that already figured it out.

Stuck on a micro-decision workflow preview

Workflow feels outdated

Pull what top products are doing right now so you're building from fresh patterns.

Workflow feels outdated workflow preview

Set up in under a minute.

One config block. Works with your favorite AI tools.

  1. 1

    Add the MCP server

    Register Granola in your AI tool using the config below.

    ~/.cursor/mcp.json
    {
  "mcpServers": {
    "granola": {
      "type": "http",
      "url": "https://mcp.granola.ai/mcp"
    }
  }
}
  2. 2

    Set up in Claude Code

    Run: claude mcp add granola --transport http https://mcp.granola.ai/mcp Run /mcp and authenticate with Granola

  3. 3

    You're set

    Granola MCP is connected. Start prompting with real references.

Frequently asked questions

What can I do with Granola MCP?+

Granola MCP lets your agent query meeting notes and transcripts inside your ai tools without switching tools or copy-pasting data.

What research data can my agent access?+

Your agent can pull research insights from Granola — search, compare, and summarize results in the context of your project.

Can my agent compare results across sources?+

Yes. Ask your agent to compare patterns, metrics, or examples from Granola side by side and summarize actionable takeaways.

What workflows does this support?+

Research, audits, competitive scans, and research planning — your agent uses Granola as live context while you build.

Can I use this for research and discovery?+

Yes. Explore research opportunities, surface examples, and turn findings into next steps — all from a single prompt in your AI tool.

Your AI agents are guessing. They don't have to.

Meeting notes and transcripts inside your AI tools

Install MCPVisit website