How to Use the Cognee MCP in OpenAI Agents SDK

Feed structured knowledge graphs directly to your OpenAI Agents SDK pipelines for reliable, graph-backed decisions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cognee MCP to OpenAI Agents SDK

Create your Vinkius account to connect Cognee 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 Cognee with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build graphs from raw text inside OpenAI Agents SDK

`cognee_add_data` sends unstructured documents straight from your local files into a persistent database. This tool acts as the entry point, prepping raw text so your agents build a clean memory layer without manual data cleaning. Once the raw data sits in the system, your agent triggers `cognee_cognify` to extract entities and map out their relationships. This step builds the actual graph structure, turning messy text into a clean network of facts that your OpenAI Agents SDK queries on demand.

Extract deep relationship insights for multi-agent handoffs

`cognee_get_insights` pulls structured entity relationships directly from your graph. Instead of passing massive, messy text blobs between your specialized agents, you pass precise nodes and connections. This approach cuts down on token waste and prevents your agents from losing context during complex tasks. It gives your OpenAI Agents SDK system a shared, high-fidelity memory that persists across different agent lifecycles.

Search the knowledge graph with natural language

`cognee_search` queries your knowledge graph using semantic search and graph traversal. Your agent gets direct answers backed by real entity connections instead of guessing based on raw vector matches. Connecting this MCP Server to your OpenAI Agents SDK setup takes only a few lines of code. Your agents auto-discover these tools, letting you focus on writing guardrails and system prompts rather than database connectors.

Setup guide

Set up Cognee 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 Cognee tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Cognee 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="Cognee Agent",
            instructions="You have access to Cognee 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 Cognee. 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 Cognee 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 Cognee MCP in OpenAI Agents SDK

You register the MCP Server using the streamable HTTP parameters. Run pip install openai-agents, set up the connection URL, and pass the server directly into your Agent constructor to let the SDK auto-discover all four tools instantly.

Yes. Initialize the connection inside an async context manager to keep your agent loops non-blocking when running heavy graph queries.

Write custom input validators in the SDK to check arguments before they reach the MCP tools. This prevents malformed data from hitting your graph during runtime execution.

The Vinkius managed platform runs each server in an isolated sandbox. It scales to handle parallel requests from multiple agents without dropping connections or slowing down graph traversals.

Your unstructured text and relationship graphs process inside a secure, zero-trust V8 sandbox. Vinkius hosts the server ephemerally, ensuring your raw files and relationship graphs are never cached or exposed to third parties.

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