How to Use the Cognee MCP in Claude

Q: How do I query my Cognee graph directly from Claude Desktop?

You just ask Claude in plain English. Your agent uses the cogneesearch tool from the MCP Server to traverse the graph and pull back exact node connections.

Q: Can I load local markdown files into Cognee with Claude Desktop?

Yes, you can feed any local text document directly to the cogneeadddata tool. Claude reads the file from your local disk and stages it for graph creation.

Drop raw text into Claude Desktop and watch it build a local, searchable knowledge graph with this Cognee integration.

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 Claude Desktop

Create your Vinkius account to connect Cognee to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build structured graphs with this Claude Desktop MCP Server

The `cognee_add_data` tool loads raw text files or documents straight from your local drive into the system cache. This acts as the staging ground before any graph processing begins. Once staged, your agent triggers the processing pipeline. It prepares your unstructured files so they can be parsed into actual nodes and connections.

Extract entities and relationships on the fly

The `cognee_cognify` tool parses your staged data to extract entities and discover hidden relationships. It automatically generates vector embeddings and maps out the connections. This creates a solid graph structure right on your machine. Your agent uses this map to understand how different concepts connect without manual tagging.

Query your graph with natural language

The `cognee_search` tool runs natural language queries across your knowledge base using graph traversal. It combines semantic search with structural relationships to find exact answers. You can also run `cognee_get_insights` to pull high-level summaries of these connections. This MCP tool gives your agent the context needed to answer complex questions about your data.

Setup guide

Set up Cognee MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Cognee MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Cognee MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under cognee-mcp.

json

{
  "mcpServers": {
    "cognee-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

You just ask Claude in plain English. Your agent uses the `cognee_search` tool from the MCP Server to traverse the graph and pull back exact node connections.

Yes, you can feed any local text document directly to the `cognee_add_data` tool. Claude reads the file from your local disk and stages it for graph creation.

The graph processing runs on Vinkius managed servers, while your Claude Desktop client acts as the interface. This keeps heavy graph computations off your local machine.

No, Vinkius manages the underlying infrastructure. You connect your client using the provided endpoint token and start staging data immediately.

Your raw text documents and generated graph nodes are processed inside a secure, isolated V8 sandbox. This network boundary ensures your proprietary knowledge base remains completely private.

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