Skip to main content
The 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
  • Taking action - Create and update entities, Scorecards, Initiatives, Workflows, and more from your MCP client, then run Workflows and check the status of each run
  • 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.
Last modified on October 12, 2026