Cortex MCP is a Model Context Protocol server that provides access to the Cortex API. It uses relevant context from your workspace, ensuring awareness of your system's structure when answering questions. You can query information in natural language, powering faster decisions and efficient processes. The server is designed to be deployed with Docker and works with MCP-compatible clients such as Claude Desktop, Claude Code, Cursor, VSCode, and Warp; sample configurations are provided for each client. To use it, you need an MCP client and a Cortex Personal Access Token, with docker run commands pre-configured to pass CORTEX_API_TOKEN. For self-managed Cortex deployments, you can also set CORTEX_API_BASE_URL. The README provides example questions like identifying the right incident owner or listing platform services, illustrating how workspace context enhances responses about incidents and architecture. This is an early research preview; user feedback and bug reports are encouraged via GitHub Issues or support channels.