How to Use the Cognee MCP in Claude Code

Add a knowledge graph to your terminal with Cognee and Claude Code.

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 Code

Create your Vinkius account to connect Cognee to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Claude Code ingests your data

Pipe your documents into `cognee_add_data` from your terminal. It’s the fastest way to get your project info into the graph. Claude Code handles the ingestion as part of your existing CLI routine. It's built for speed and automation.

Build graphs with Claude Code

Run `cognee_cognify` to turn your text into a searchable structure. It identifies entities and generates embeddings for your graph. Your agent uses this structure to navigate complex project dependencies from the command line. It's perfect for CI/CD pipelines that need actual project context.

Get insights in Claude Code

Use `cognee_get_insights` to extract data directly into your terminal output. It’s a clean way to view relationships without opening a browser. Claude Code reads these insights to automate decisions in your shell scripts. You get the power of a knowledge base in a headless environment.

Setup guide

Set up Cognee MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see cognee-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Cognee transactions." It will automatically discover and invoke the available Cognee tools.

Terminal

claude mcp add --transport http cognee-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Cognee MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "cognee-mcp": {
      "type": "url",
      "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 Code

You add the server via your config file or the command line. Once connected, Claude Code gains the ability to traverse your knowledge graph using standard MCP tools.

It works perfectly. Because the server is headless, your automation scripts can query the graph during deployment to verify logic based on your project docs.

It can. By using the search tools, the agent retrieves context-aware answers that it uses to pipe data into other terminal commands.

You stop relying on grepping through files. You get a graph-aware agent that understands the structure of your project docs from the command line.

Your data is stored in an ephemeral sandbox managed by Vinkius. We use strict token-based security to ensure your raw text and graph nodes remain private and scoped only to your sessions.

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