Categories › Knowledge & Everyday › Research, papers & reference data
Evidence-first registry of real-world APIs for AI agents, with verified metadata and comparison.
Remote server: your requests and data go to mcp.realworldapis.com. Claude Code: claude mcp add --transport http realworldapis https://mcp.realworldapis.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
find_api_for_task — Find the best APIs for a natural-language physical-world task. Use this for open-ended task or outcome-based recommendations; use search_apisearch_apis — Search the canonical registry when you already know keywords or exact requirements. All supplied filter groups combine with AND logic; arraysearch_capabilities — Search the canonical 770-capability Verified/High decision graph directly. Use this when the question is about what an agent can actually doverify_requirement — Verify whether one specific API can satisfy one exact requirement using the canonical Verified/High capability graph plus linked assertion eget_api — Retrieve one canonical API decision profile when you already know its name or slug. The response includes the full Verified/High capability compare_apis — Compare 2–8 already-known APIs side by side using canonical catalog fields plus capability-graph summary fields such as verified capability compose_workflow — Propose a planning-only API workflow from 1–8 structured steps. Include the complete original goal and restrictions. Returns canonical candiNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.