How to Use the Granola MCP in Pydantic AI

Q: How do I fetch metadata for a specific meeting?

Use the getmetadata MCP tool by passing the document ID. This returns the meeting date, title, and other structural details.

Validate meeting summaries and action items with type-safe Pydantic AI pipelines.

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 Pydantic AI

Create your Vinkius account to connect Granola to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce runtime type safety on your MCP Server

The `get_action_items` tool delivers structured meeting tasks directly to your Pydantic AI agent. Because this framework validates every incoming payload, any malformed task data triggers an immediate runtime error instead of silently corrupting your database. This strict validation ensures that task lists match your exact Python schemas before they reach your downstream code. You get absolute predictability, even when dealing with unpredictable meeting transcripts.

Validate complex meeting structures at runtime

The `get_content` tool retrieves the full structured layout of a meeting document. Pydantic AI parses this structure against your defined models, ensuring that headings, bullet points, and text blocks conform to your application's expectations. If a meeting note is missing required fields, the agent rejects the payload instantly. This mechanism prevents your LLM from hallucinating fields that do not exist in the raw Granola source.

Query structured summaries with zero silent errors

The `get_summary` tool provides AI-generated overviews that your agent can parse into structured JSON. By using Pydantic AI, you guarantee that the extracted summary fields match your system's required data types. You can combine this with `list_recent` to build a clean, validated dashboard of your latest team decisions. The entire pipeline runs over secure SSE or HTTP transports hosted on Vinkius.

Setup guide

Set up Granola MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "granola-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Granola tools.",
)

result = await agent.run("List recent Granola transactions")
print(result.output)

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 Pydantic AI

Use the MCPToolset class with your Vinkius HTTP endpoint URL. Pass this toolset directly into your Agent constructor to register all 12 MCP tools.

The framework raises a validation error immediately. This prevents your agent from operating on incomplete or corrupted meeting data.

Yes, Pydantic AI requires the MCP server to run externally. Vinkius hosts the server for you, providing a stable HTTP endpoint for your agent to connect to.

Use the get_metadata MCP tool by passing the document ID. This returns the meeting date, title, and other structural details.

The framework processes your meeting notes and action items purely in-memory during validation. Vinkius handles the underlying connection using single-use tokens and zero-trust isolates.

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