
Ask: "What's breaking in production right now?" Runheed records errors from your Node.js or Python apps, groups them, and lets your AI read each one with its stack trace, the breadcrumbs that led to it and the request it failed on.
Your AI can look at trends and project health, then fix the code and mark the error resolved with a note of the fix. It works in your AI Code too, so the agent that wrote the code can read what broke in production and fix it in the same session.
https://runheed.com/api/mcpRunheed holds the production errors reported by this workspace's apps. and list error groups with their IDs; and return one group in full; marks a group fixed and takes the fixing commit as its comment.
None in the store listings or on the server