Connect the Granola MCP server to Unblocked to give AI agents live meeting notes context

Granola turns calls into notes — the summary, the attendees, and what you jotted down while the conversation happened. Those notes often hold the clearest record of why a feature was scoped the way it was, but they sit in Granola while the work happens in the editor. Granola’s MCP server exposes meeting notes to AI agents, and Unblocked connects to it once so every agent can ask about a meeting without its own Granola setup.

This is a third-party MCP server: Granola hosts and maintains it, and Unblocked connects to it as a verified MCP server. Nothing is ingested or indexed — Unblocked calls the read-only tools you select at the moment a question needs them, so answers reflect the notes the authorizing account can see in its active Granola workspace right now.

Wiring Granola’s MCP server straight into an agent gives it notes from one meeting at a time. Unblocked’s Context Engine reasons across those results and your other sources — following a requirement agreed in a customer call to the ticket that recorded it, the pull request that built it, and the Slack thread where engineering pushed back — and returns one cited answer.

Once connected, any MCP-compatible coding agent — Claude Code, Cursor, Devin, GitHub Copilot, Codex — reaches Granola context through a single Unblocked MCP server connection.

What you get

• Live meeting notes and transcripts — Agents list meetings and read notes, summaries, attendees, and — on paid Granola plans — raw transcripts, through Granola’s own MCP server.
• One connection for every agent — Connect Granola to Unblocked once. Claude Code, Cursor, Codex, and GitHub Copilot reach it through the Unblocked MCP server, with no per-agent Granola configuration.
• Read-only, workspace-safe control — Only read-only tools are offered, so agents can’t switch your active Granola workspace or sign the connection out. Choose which tools Unblocked may call from Settings → Data Sources.
• Context Engine reasoning — Granola results are reconciled with your code, pull requests, tickets, and conversations, so a decision captured in a meeting note leads to the work it shaped — with citations.

Prerequisites

• An Unblocked account (free to start).
• A Granola account that can sign in through Granola’s browser OAuth; on Enterprise workspaces, an admin must enable the note scopes members can reach through MCP.
• An MCP-compatible coding agent (Claude Code, Cursor, Devin, etc.) to use the context in your editor.

Step 1: Connect Granola to Unblocked

1. In Unblocked, go to Settings → Data Sources → Connect another data source, and under Documentation select Granola.
2. The Granola MCP server URL is filled in for you. Choose OAuth, click Connect, and sign in to Granola to authorize Unblocked.
3. Once Unblocked discovers the server’s tools, select the read-only tools it may use and click Save Settings.

Step 2: Install the Unblocked MCP server

On macOS or Linux, one command auto-detects and configures the supported agents on your machine:

On Windows, or when you prefer remote MCP, add the server manually using the configuration below, or follow the manual install guide .

claude mcp add -s user --transport http unblocked https://getunblocked.com/api/mcpsse

{
  "mcpServers": {
    "unblocked": {
      "url": "https://getunblocked.com/api/mcpsse"
    }
  }
}

https://getunblocked.com/api/mcpsse

Granola hosts and maintains this MCP server. Unblocked calls only the read-only tools you select, at the moment a question needs them:

• query_granola_meetingsAnswers a natural-language question by chatting with your Granola meeting notes.
• list_meetingsLists accessible meetings with their ID, title, date, and attendees, optionally filtered by folder on paid plans.
• get_meetingsReturns accessible meeting notes, including title, date, attendees, private notes, and summarized notes.
• get_meeting_transcriptReturns the raw transcript of a meeting. Available on paid Granola plans.
• list_meeting_foldersLists the folders you can access, with each folder’s title, description, and note count. Available on paid Granola plans.

To give Claude Code, Cursor, GitHub Copilot, Codex, or another MCP-compatible AI coding agent access to Granola context, connect Granola to Unblocked and add the single Unblocked MCP server to your agent.

Unblocked acts as the MCP context layer for your Granola data, searching meeting notes and transcripts alongside your other connected sources and returning cited results through these tools:

• context_researchResearches a question across your connected sources and calls the Granola tools you selected when meeting notes or transcripts are relevant, returning a synthesized answer with citations.
• context_get_urlsFetches the full content behind URLs your agent encounters across connected sources — Jira, Linear, Notion, Confluence, Slack, GitHub, and more.

Questions you (or your agent) can ask Unblocked about your Granola data:

• What did the customer ask for in Tuesday’s onboarding call, and is there a ticket or pull request for it?
• Summarize the notes from the API versioning meeting and show me where the code matches what we agreed.
• Which follow-ups from this week’s product review never made it into Linear?
• Did anyone in a recent meeting raise the rate-limit concern that’s now in this Slack thread?