CLIRank

About CLIRank

CLIRank is an API directory built for coding agents rather than for humans browsing docs. It scores hundreds of APIs on agent-friendliness using a transparent eight-signal rubric covering the things that actually determine whether an agent can use a service unattended: authentication method, whether a CLI tool exists, pricing transparency and headless operation among them. The critical design decision is that the scorecard is queryable at runtime. CLIRank ships an MCP server — added with a single npx command to any MCP-compatible client — so Claude Code, Codex, Cursor, Copilot, Cline or Windsurf can consult the rubric before choosing which API to integrate, instead of guessing from training data that may be years stale. That flips a directory from something a developer reads into something an agent calls mid-task. Around the scores sit comparison views, leaderboards, task-oriented and best-of groupings, a library, community-sourced agent reviews, and a submission route for APIs not yet covered. There is also a plain HTTP API for clients that are not MCP-based. The whole thing is free, open and requires no authentication, which is consistent with the use case — an agent cannot be asked to complete a signup flow — and means adoption costs nothing more than pasting a config block into your client's MCP settings.

Key Features

CLIRank Pros & Cons

Tags