How to Use the Notion MCP in OpenAI Agents SDK

Q: How do I connect the Notion MCP server to the OpenAI Agents SDK?

Install openai-agents and initialize MCPServerStreamableHttp with your Vinkius endpoint. Pass this server instance into your Agent constructor using the mcpservers list. The agent automatically discovers all 14 workspace tools.

Q: Can my agent read the actual text content of a page?

Yes, but you must use getblocks to read the hierarchical page content. The standard getpage tool only retrieves page metadata and properties, not the body text itself.

Ship production-grade Python agents that safely edit databases and write docs using the OpenAI Agents SDK and this Notion 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 OpenAI Agents SDK

Create your Vinkius account to connect Notion to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find and modify workspace data

Look, finding things in a massive workspace is annoying. The `search_pages` and `search_databases` tools let your agent find specific UUIDs across your workspace. Your Python agent executes fuzzy text queries to locate the exact target before running updates. This prevents errors when targeting deeply nested structures. Once the agent has the UUID, it runs `get_page` or `get_database` to read the structure. This two-step lookup keeps your agent on track and avoids breaking your database schemas.

Build structured databases on the fly

The `create_database` and `create_page` tools allow your agent to build structured tables and insert new rows. You define columns with specific property types directly from your Python code. This lets your agent spin up tracking tables when a new project starts. For existing tables, the agent uses `update_page_properties` to modify specific cells. This keeps your data clean without manual copy-pasting.

Safe block edits via OpenAI Agents SDK

The `append_block_children` tool inserts rich text, paragraphs, or lists into any Notion page. Your agent structures the content as a JSON array of block objects to add notes or logs. This handles the raw formatting so your Python code stays clean. If an agent makes a mistake, it calls `archive_page` or `delete_block` to clean up. With the SDK's built-in guardrails, you inspect these destructive actions before they execute via the MCP server.

Setup guide

Set up Notion MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Notion tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Notion tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Notion tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Notion Agent",
            instructions="You have access to Notion tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` and initialize `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this server instance into your Agent constructor using the `mcp_servers` list. The agent automatically discovers all 14 workspace tools.

Yes. You configure this on the Vinkius platform or restrict tool execution within your agent's system instructions. Setting `cacheToolsList=True` in your Python setup improves startup performance by caching the schema definitions.

The SDK handles execution, but the MCP server manages the underlying API limits. When calling `query_database` repeatedly, implement backoff logic in your agent's execution loop to stay within limits.

Yes, but you must use `get_blocks` to read the hierarchical page content. The standard `get_page` tool only retrieves page metadata and properties, not the body text itself.

Your Notion pages, databases, blocks, and user lists stay private. Vinkius runs this server in an isolated, zero-trust V8 sandbox. Your credentials and database content are never stored or used to train models.

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