How to Use the Granola MCP in AutoGen

Q: How do I register the Granola MCP Server tools in AutoGen?

Install autogen-extmcp and use mcpservertools with your Vinkius HTTP URL. Pass the resulting tool list to your AssistantAgent constructor to convert the MCP schemas.

Q: Can AutoGen agents search across my Granola meetings?

Yes, agents can call searchdocuments to find relevant past discussions. They use this search capability to resolve debates about historical project decisions.

Q: How do AutoGen agents handle recent Granola documents?

The agents use listrecent to pull the latest 20 meetings. They then coordinate to parse the most relevant notes first based on current project priorities.

Q: Where is my Granola meeting metadata processed?

All tool calls, including getmetadata, run inside Vinkius's secure, isolated V8 sandbox. This MCP connection ensures your meeting details and participant lists are never exposed to public networks.

Let AutoGen agents debate project decisions using real-time transcripts and action items pulled from Granola.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Granola MCP to AutoGen

Create your Vinkius account to connect Granola to AutoGen 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 Granola with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven Meeting Analysis

This MCP Server exposes `get_transcript` so your AutoGen agents can debate the details of a meeting. One agent can analyze the transcript for technical requirements while another flags timeline risks. The agents negotiate their findings in a shared conversation thread, ensuring a balanced summary. This prevents a single agent from misinterpreting raw meeting discussions.

Collaborative Action Item Auditing in AutoGen

The `get_action_items` tool retrieves extracted tasks from Granola documents for your agent group to review. A coordinator agent can assign these tasks to specific team members based on the discussion context. If a task is ambiguous, a critic agent calls `get_content` to verify the original phrasing. This collaborative verification ensures that the final task list is accurate before export.

Automated Folder Organization

The `list_folders` tool enables AutoGen agents to inspect your workspace structure and organize meeting notes. Your agents can debate where a newly created meeting document belongs based on its metadata. By calling `list_documents` and `get_metadata`, the agents determine the correct folder placement. This automates workspace maintenance without human intervention.

Setup guide

Set up Granola MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Granola tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Granola_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Granola data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Granola_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Granola data")
    print(result.messages[-1].content)

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 Granola. 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 Granola 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 Granola MCP in AutoGen

Install `autogen-ext[mcp]` and use `mcp_server_tools` with your Vinkius HTTP URL. Pass the resulting tool list to your `AssistantAgent` constructor to convert the MCP schemas.

Yes, agents can call `search_documents` to find relevant past discussions. They use this search capability to resolve debates about historical project decisions.

The agents use `list_recent` to pull the latest 20 meetings. They then coordinate to parse the most relevant notes first based on current project priorities.

Yes, agents don't waste tokens on raw dialogue when they can call `get_summary` to grab high-level details. This saves token costs when the agents only need a quick status update.

All tool calls, including `get_metadata`, run inside Vinkius's secure, isolated V8 sandbox. This MCP connection ensures your meeting details and participant lists are never exposed to public networks.

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