Cursor Integration

If you’re looking to unify your code exploration in Python repositories, Cursor provides an intuitive interface to interact with cognee’s MCP server directly.

If you are using Visual Studio Code, you can explore our Roo or Cline integration guides instead.

By integrating Cursor and cognee, you can effortlessly:

Generate knowledge graphs from your codebase
Access code search capabilities
Explore advanced analysis tools without leaving your IDE

Let’s quickly set up cognee’s MCP server in Cursor, ensuring you can query your codebase and retrieve insights.

Why Use Cognee with Cursor?

Cognee specializes in building detailed knowledge graphs and retrieve accurate data based on user queries. Together with Cursor, you get:

Streamlined Development Experience: Interact with cognee’s code analysis directly from Cursor’s Composer.
Enhanced Code Understanding: Find out dependencies and relationships in your code base easily, and quickly search across large codebases.
Efficiency Gains: No need to switch between terminals or external apps—simply invoke cognee’s powerful tools from within your IDE.

Prerequisites

Before proceeding, ensure you have the following:

Cursor installed on your machine.
A local copy of the cognee repository.
An LLM API key (default setup uses OpenAI, e.g., sk-...).

Integration Steps

1. Install Cursor

Visit the official Cursor website to download Cursor.
Follow the on-screen instructions to install Cursor on your operating system.
Once installed, open Cursor to verify everything is functioning properly.

2. Clone and Navigate to Cognee

Open your terminal and run:

git clone https://www.github.com/topoteretes/cognee
cd cognee/cognee-mcp

3. Install Dependencies

Cognee uses the uv package manager for setup and runtime:

If you’re on macOS, install uv via Homebrew:
```
brew install uv
```
Move to the cognee-mcp directory and sync dependencies:
```
uv sync --reinstall
```

This process ensures cognee’s environment is fully configured and ready to run.

4. Create a Run Script for Cognee

Inside your preferred scripts directory (e.g., in your project directory), create a file named run-cognee.sh.
Make it executable and add the following contents:

#!/bin/bash
export ENV=local
export TOKENIZERS_PARALLELISM=false
export LLM_API_KEY=your-API-key
uv --directory /{cognee_root_path}/cognee-mcp run cognee

Remember:

Update /{cognee_root_path}/cognee-mcp to the full path of your cloned cognee repo.

Replace your-API-key with your actual API key.

5. Add a New MCP Server in Cursor

Launch Cursor, and click the Gear Icon to open Settings.
Navigate to Features > MCP.
Click on + Add New MCP Server.

In the Add MCP Server modal, set the following:

Type: Stdio
Name: Cognee (or any nickname you prefer)
Command: Point this to your script:
```
sh /{script_root_path}/run-cognee.sh
```

Save this configuration. You should see your new entry in the MCP settings list.

6. Refresh and Verify Cognee in Cursor

In the MCP settings, locate your newly added cognee server.
Click the Refresh button (often in the top-right corner of the server’s card) to have Cursor attempt to connect.

If all goes well, you should see a list of available tools from cognee (e.g., codify). This indicates cognee’s MCP server is running correctly, and Cursor has successfully loaded the server’s capabilities.

7. Use Cognee in Cursor’s Composer

Open the Composer in Cursor.
Make sure Agent and not Ask is selected.
Issue a prompt referencing cognee tools. Cursor will pass your request to the cognee MCP server, and results will be displayed directly in the Composer. For instance:

Remember: Use the CODE search type to query your code graph. Tip: For larger codebases, consider incremental indexing or caching to speed up analysis.

You’ve now set up cognee’s MCP server with Cursor! Enjoy a richer, more powerful code exploration experience right inside your IDE.

Join the Conversation!

Have questions or feedback? Join our community to connect with professionals, share insights, and get answers to your questions!

Roo Code Reference