# Cortex MCP The [Cortex MCP](https://github.com/cortexapps/cortex-mcp) is a Model Context Protocol server that brings your engineering data into the tools your team already works in, enabling natural language queries across your catalog, Scorecards, metrics, and Initiatives. It provides: * **Natural language querying** - Ask questions in plain English rather than constructing API calls directly * **Contextual awareness** - Maintains awareness of your workspace's structure when answering questions, so responses are grounded in your org's actual data * **AI-assisted insights** - Synthesizes Eng Intelligence metrics, Scorecard status, ownership, and initiative data into actionable recommendations * **Cross-tool availability** - Surfaces inside the tools your team already uses, making it an in-workflow intelligence layer rather than a standalone API * **Prompt-driven workflows** - Supports complex, multi-part queries that combine data from multiple Cortex systems in a single response * **Documentation querying** - The remote MCP implementation includes a `query_docs` tool that lets you ask questions against Cortex's own documentation and knowledge base in natural language ## Cortex MCP overview More of a visual learner? Watch the Cortex MCP in action in this short video. {% embed url="" %} --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.cortex.io/get-started/mcp.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.