How to Use the Cognee MCP in Pydantic AI

Run type-safe graph queries with Pydantic AI using this managed 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 Cognee MCP to Pydantic AI

Create your Vinkius account to connect Cognee 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 Cognee with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate graph extractions with Pydantic AI

`cognee_cognify` structures raw text into a clean knowledge graph by extracting entities and mapping their relationships. When using this tool, your Pydantic AI agent validates the schema of every returned node to ensure structured accuracy. If the graph returns unexpected data structures, the system catches the mismatch immediately. This strict approach prevents corrupt data from polluting your database during ingestion.

Ingest raw text into a type-safe database

`cognee_add_data` loads unstructured documents and raw text strings directly into the knowledge base. It handles the initial storage phase before the graph construction begins. Your agent coordinates this process using a unified MCP connection. This keeps your data pipeline clean and ensures your ingestion scripts don't suffer from silent failures.

Query entity connections using this MCP Server

`cognee_get_insights` retrieves structured relationships from the graph. The tool returns clean, typed data that your Pydantic AI models parse into strict Python classes. Run natural language queries using `cognee_search` to combine semantic search with graph traversal. This tool gives your agent context-aware answers that conform to your defined schemas.

Setup guide

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

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

result = await agent.run("List recent Cognee 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 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 Pydantic AI

Use the unified MCPToolset class and pass the Vinkius server URL. Avoid the deprecated MCPServerHTTP class, as the unified toolset is the standard way to load external tools.

Your Pydantic AI agent raises a validation error instantly. This prevents your application from processing malformed graph data or hallucinated fields.

Yes. The server supports both Streamable HTTP and SSE transports, and Vinkius manages the endpoint so you only need to supply the connection token.

Yes. Because Pydantic AI is model-agnostic, you can use these graph tools with local LLMs, OpenAI, or Anthropic models while maintaining strict runtime validation.

All entities, document chunks, and relationship graphs are processed inside an ephemeral, zero-trust V8 sandbox. No data is stored on Vinkius servers after your session terminates, keeping your private knowledge base secure.

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