Categories › AI & Agents › Multi-agent, orchestration & workflows
The governed runtime for agent skills. Search the catalog and inspect a skill before running it.
Remote server: your requests and data go to api.runx.ai. Claude Code: claude mcp add --transport http runx https://api.runx.ai/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
search_skills — Find runx skills by what they do. Returns each match with its skill id, publisher, description, latest version, and trust tier, so a caller get_skill — Read one runx skill in full before running it: its manifest, the authority it asks for, its publisher and trust signals, and the exact commaNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.