Granola MCP

CALL ANY TOOL

List notes, get summaries, search transcripts, and retrieve action items via Granola's MCP server.

granolamcp_notes_list

List notes

List all accessible meeting notes via the Granola MCP protocol.

Parameters

Name

Type

Required

Description

limit

integer

Optional

Max notes to return

after

string

Optional

ISO 8601 lower bound

granolamcp_note_get

Get note

granolamcp_note_summary

Get summary

granolamcp_search

Search notes

granolamcp_attendees_list

List attendees

Build your Agent

Drop the toolkit in, point it at the user, and your meeting intelligence agent can use Granola MCP from the first run.

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["granolamcp"], toolNames: ["granolamcp_notes_list", "granolamcp_note_get", "granolamcp_note_summary"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["granolamcp"], toolNames: ["granolamcp_notes_list", "granolamcp_note_get", "granolamcp_note_summary"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["granolamcp"], toolNames: ["granolamcp_notes_list", "granolamcp_note_get", "granolamcp_note_summary"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

Copied

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/granolamcp",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start using Granola MCP.

Search & recall

Copy the prompt

Copied

List all meeting notes from this week.

Copy the prompt

Copied

Search notes for [topic].

Copy the prompt

Copied

Get the summary of [meeting name].

Copy the prompt

Copied

Find notes with [person name] as attendee.

Action & follow-up

Copy the prompt

Copied

Get action items from [meeting name].

Copy the prompt

Copied

List all open action items this week.

Copy the prompt

Copied

Who attended [meeting name]?

Copy the prompt

Copied

Find notes where [decision] was made.

Reporting

Copy the prompt

Copied

Summarize all customer calls this month.

Copy the prompt

Copied

Which meetings had no action items?

Copy the prompt

Copied

List notes from [account name] this quarter.

Copy the prompt

Copied

Find meetings that ran over 60 minutes.

SEE HOW AUTH WORKS

Users authorize Granola MCP once. Their credentials stay vaulted, every call is checked, and every action is logged.

1

Authorize

Your user connects

Granola MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Granola MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Granola MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Granola MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other meeting intelligence agents and MCP connectors. Working code, live demos, fork what fits.

SALES

Deal intelligence agent

Combine Gong, Attio, and Slack signals to surface deal risks and next-best actions. Updated after every call.

ENGINEERING

Engineering standup agent

Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Granola MCP today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Granola MCP as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Granola MCP bearer token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Granola MCP?

Yes. Pass a tool name filter to listScopedTools so the meeting intelligence agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Granola MCP.

What happens when a user revokes Granola MCP access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Does this connector access the same workspace as the Granola connector?

Yes. Both connect to the same Granola workspace via the user's token. The authorizing user's scope determines which notes are accessible. There is no difference in data access between the two connector types.

Tools your meeting intelligence agent reaches for on Granola MCP, scoped per user.