> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cognee.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Llms mcp

# Cognee MCP Documentation

> Model Context Protocol docs for Cognee MCP, including setup, tools, transport modes, and client integrations.

See the full overview at [https://docs.cognee.ai/llms.txt](https://docs.cognee.ai/llms.txt).

## MCP Core

* [Overview](https://docs.cognee.ai/cognee-mcp/mcp-overview.md): Connect Cognee's knowledge graph platform with MCP-compatible AI tools
* [Quickstart](https://docs.cognee.ai/cognee-mcp/mcp-quickstart.md): Get Cognee MCP running in minutes with Docker
* [Tools Reference](https://docs.cognee.ai/cognee-mcp/mcp-tools.md): Complete reference for all Cognee MCP tools and operations
* [Local Setup](https://docs.cognee.ai/cognee-mcp/mcp-local-setup.md): Deploy Cognee MCP server from source for development and customization
* [Cognee Cloud & MCP](https://docs.cognee.ai/cognee-mcp/mcp-cloud-connection.md): How to connect the Cognee MCP server to Cognee Cloud

## Client Integrations

* [Claude Code](https://docs.cognee.ai/cognee-mcp/integrations/claude-code.md): Claude Code is Anthropic's command-line AI assistant with built-in MCP support. It runs in your terminal and can access MCP servers configured in your project or user settings.
* [Claude Desktop](https://docs.cognee.ai/cognee-mcp/integrations/claude-desktop.md): Claude Desktop is Anthropic's native app for macOS and Windows. It supports MCP servers through a config file that you edit manually — no command-line setup required after initial configuration.
* [Cursor](https://docs.cognee.ai/cognee-mcp/integrations/cursor.md): Cursor is an AI-powered code editor built on VS Code with native support for the Model Context Protocol. It provides AI assistance through its Composer interface and chat panel.
* [Codex](https://docs.cognee.ai/cognee-mcp/integrations/codex.md): Codex is OpenAI's coding agent with built-in MCP support. You can register Cognee MCP once, then use Cognee memory and retrieval tools directly in your Codex sessions.
* [Continue](https://docs.cognee.ai/cognee-mcp/integrations/continue.md): Continue is an open-source AI coding assistant for VS Code and JetBrains IDEs. It supports MCP servers through YAML configuration files in your workspace.
* [Cline](https://docs.cognee.ai/cognee-mcp/integrations/cline.md): Cline is a VS Code extension that provides AI assistance with support for MCP servers. It enables natural language interactions with external tools directly in your development environment.
* [Roo Code](https://docs.cognee.ai/cognee-mcp/integrations/roo-code.md): Roo Code is a VS Code extension that provides AI-powered development assistance with support for MCP servers. It enables direct interaction with external tools through natural language.
* [Goose](https://docs.cognee.ai/cognee-mcp/integrations/goose.md): Goose is an open-source AI coding assistant by Block with built-in MCP support. It runs as a CLI or desktop app and connects to MCP servers through its extensions system.
* [Python Agent](https://docs.cognee.ai/cognee-mcp/integrations/python-agent.md): Connect your own Python LLM agent to Cognee MCP to give it persistent knowledge graph memory. The mcp Python SDK lets you call all Cognee MCP tools programmatically — no IDE or chat client required.