How to Use the Notion MCP in Pydantic AI

Q: How do I initialize the Notion MCP server in Pydantic AI?

Install pydantic-ai-slimmcp and use the unified MCPToolset("http://...") class. Pass this instance into the toolsets argument of your Agent. Do not use the deprecated HTTP server classes.

Build type-safe Python agents that manage Notion workspaces with strict Pydantic AI validation and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Notion MCP to Pydantic AI

Create your Vinkius account to connect Notion 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 Notion with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe database queries

We don't do silent failures here. The `query_database` and `get_database` tools return structured workspace data that Pydantic AI validates at runtime. If a database schema changes, the framework raises a validation error immediately. This prevents corrupted data from entering your agent pipelines. Your agent uses `search_databases` to find the target database UUID first. This guarantees you are querying the correct table before parsing its properties.

Strict page and block manipulation

The `create_page` and `update_page_properties` tools require exact JSON structures that match Notion's property schema. Pydantic AI enforces these types before sending the payload to the MCP server. This eliminates raw API errors during page creation. To write body text, your agent uses `append_block_children` with a validated array of block objects. The strict typing ensures your formatting blocks are perfectly structured.

Workspace cleanup via Pydantic AI

The `archive_page` and `delete_block` tools let your agent remove outdated pages or blocks from your workspace. Because these actions are destructive, the framework's strict validation ensures your agent targets the exact UUID. This keeps your clean-up scripts safe and predictable. You can also use `update_page_title` to rename pages instead of deleting them. This preserves the page history while keeping the workspace organized.

Setup guide

Set up Notion 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": {
        "notion-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Notion 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 Notion. 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 Notion 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 Notion MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and use the unified `MCPToolset("http://...")` class. Pass this instance into the `toolsets` argument of your `Agent`. Do not use the deprecated HTTP server classes.

The framework will raise a validation error at runtime. This prevents silent failures and ensures your Python agent only processes data that strictly matches your defined schemas.

It supports both Streamable HTTP and SSE transports. Since the server must run externally, the Vinkius hosted endpoint handles the connection and authentication for you.

Yes. The framework is model-agnostic, meaning you can run your workspace automation using local models, Anthropic, or Gemini while keeping the same type-safe tools.

Every request containing Notion pages, databases, blocks, and user lists runs inside an isolated V8 sandbox. Vinkius uses a zero-trust model where your API tokens are encrypted at rest and never exposed to the LLM provider.

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