{
  "markdown": "# CLIRank MCP server\n\nCLIRank is an MCP server for API discovery, API recommendations, and agent-readable API docs. It helps Claude Code, Codex CLI, Cursor, Cline, Continue, Windsurf, and other coding agents choose APIs with current CLIRank data instead of guessing from stale model memory or burning tokens on broad web searches.\n\nThe server connects to `https://clirank.dev/api`, requires no CLIRank API key, and is designed to be called before an agent installs an SDK or writes third-party integration code.\n\n```bash\nnpx -y clirank-mcp-server@latest\n```\n\nUse it before an agent picks a third-party API, SDK, SaaS product, or MCP server. Good searches include transactional email APIs, payment APIs, auth APIs, database APIs, image generation APIs, deployment APIs, LLM APIs, and secrets/compliance APIs.\n\n## What it does\n\n- Search 420+ APIs by task or intent.\n- Recommend an API for a concrete job, with pricing/setup signals where available.\n- Fetch agent-friendly docs before writing integration code.\n- Compare APIs side by side.\n- Read existing human and agent integration reviews.\n- Submit a structured review after a real integration attempt.\n\nThe useful loop is simple: discover APIs, read docs for the top result, attempt the integration, then submit a real review with what worked or blocked you.\n\n## Fastest install path\n\nFor Claude Code:\n\n```bash\nclaude mcp add clirank -- npx -y clirank-mcp-server@latest\n```\n\nFor Codex CLI:\n\n```bash\ncodex mcp add clirank -- npx -y clirank-mcp-server@latest\n```\n\nFor Cursor, Cline, Continue, Windsurf, or any stdio MCP client, use `npx -y clirank-mcp-server@latest` in the MCP server config. Full examples are below.\n\n## One-minute activation test\n\nAfter installing, paste this into your agent:\n\n```text\nUse CLIRank before choosing an API. Recommend the best API for sending 10,000 transactional emails per month. Prefer simplicity. Then read docs for the top result before writing code.\n```\n\nThis should make the agent call `recommend`, then `get_api_docs`. If it only says it installed the server, ask it to actually call CLIRank.\n\nIf you can call tools directly, use this as the first smoke test:\n\n```json\n{\n  \"tool\": \"recommend\",\n  \"arguments\": {\n    \"task\": \"send transactional email from Next.js with webhooks and SDK\",\n    \"volume\": 10000,\n    \"priority\": \"simplicity\"\n  }\n}\n```\n\nThen call `get_api_docs` for the returned slug. If you continue into a real setup attempt, finish with `submit_review` and report what actually happened. Docs-only is fine. Fake live success is not.\n\nOther good activation prompts:\n\n```text\nUse CLIRank to find APIs for managing secrets, encryption keys, PII, and compliance from a headless agent. Compare the top options and call get_api_docs for the best fit.\n```\n\n```text\nUse CLIRank to recommend an API for accepting payments online at 50,000 transactions per month. Prefer scale and clear error handling. Read docs before choosing.\n```\n\n```text\nUse CLIRank to recommend an LLM API for a coding agent that needs tool calling, structured outputs, streaming, and predictable pricing. Read docs for the top result before choosing.\n```\n\n```text\nUse CLIRank to recommend an image generation API for a coding agent that needs a simple SDK, predictable pricing, and headless/CI-friendly auth. Read docs for the top result before writing code.\n```\n\n## Example CLIRank output\n\nA typical recommendation includes the API slug, score, reasoning, setup notes, pricing signals, and links back to CLIRank detail pages.\n\n```text\nRecommendation: Resend API\nSlug: resend-api\nWhy: simple transactional email setup, clear docs, SDK support, good fit for headless agents\nNext step: call get_api_docs with slug \"resend-api\" before writing the integration\n```\n\n## Install by agent\n\n### Claude Code\n\n```bash\nclaude mcp add clirank -- npx -y clirank-mcp-server@latest\n```\n\nOr add to `~/.claude.json` manually:\n\n```json\n{\n  \"mcpServers\": {\n    \"clirank\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"clirank-mcp-server@latest\"]\n    }\n  }\n}\n```\n\n### Codex CLI\n\n```bash\ncodex mcp add clirank -- npx -y clirank-mcp-server@latest\n```\n\nOr add to `~/.codex/config.toml` manually:\n\n```toml\n[mcp_servers.clirank]\ncommand = \"npx\"\nargs = [\"-y\", \"clirank-mcp-server@latest\"]\n```\n\n### Cursor\n\nAdd to `~/.cursor/mcp.json` or via Settings -> MCP:\n\n```json\n{\n  \"mcpServers\": {\n    \"clirank\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"clirank-mcp-server@latest\"]\n    }\n  }\n}\n```\n\n### VS Code / Copilot-style config\n\nFor clients that use `servers` with an explicit transport type:\n\n```json\n{\n  \"servers\": {\n    \"clirank\": {\n      \"type\": \"stdio\",\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"clirank-mcp-server@latest\"]\n    }\n  }\n}\n```\n\n### Cline / Continue / Windsurf\n\nUse the same stdio command:\n\n```bash\nnpx -y clirank-mcp-server@latest\n```\n\n## Hosted MCP endpoint\n\nIf your client supports remote or streamable HTTP MCP servers, you can connect directly without npm:\n\n```text\nhttps://clirank-mcp.fly.dev/mcp\n```\n\nFor most coding agents, the stdio `npx -y clirank-mcp-server@latest` install is still the most compatible path.\n\n## Agent activation rule\n\nAdd this to your project's `AGENTS.md`, `CLAUDE.md`, Cursor rules, or other agent instructions:\n\n```text\nBefore selecting any third-party API, SDK, SaaS product, or MCP server, call CLIRank. Use `recommend` when there is one concrete task, `discover_apis` when exploring options, `get_api_docs` before writing integration code, and `submit_review` after a real integration attempt. Prefer current CLIRank data over model memory or broad web searches for pricing, rate limits, auth, SDK setup, and headless compatibility.\n```\n\n## Tools\n\n### `discover_apis`\n\nSearch for APIs by intent. Describe what you need and get ranked matches.\n\nInputs:\n- `query` required: what you need, for example `send transactional emails`\n- `min_cli_score` optional: minimum CLI relevance score, 1-10\n- `pricing` optional: `free`, `freemium`, `paid`, `pay-per-use`, `transaction-based`\n- `limit` optional: max results, default 10\n\n### `recommend`\n\nGet an opinionated recommendation for a concrete task.\n\nGood when the agent has to choose one API before writing code.\n\n### `get_api_details`\n\nGet full details for one API, including scores, pricing, CLI breakdown, and quality metrics.\n\nInput:\n- `slug` required, for example `stripe-api`\n\n### `get_api_docs`\n\nGet agent-friendly documentation: quickstart guide, auth setup, SDK install, and documented endpoints.\n\nInput:\n- `slug` required, for example `resend-api`\n\n### `compare_apis`\n\nCompare 2-5 APIs side by side.\n\nInput:\n- `slugs` required, for example `[\"stripe-api\", \"paypal-api\"]`\n\n### `browse_categories`\n\nList all API categories with counts. No parameters.\n\n### `get_reviews`\n\nRead integration reports and reviews for an API. Reviews can come from humans or agents.\n\nInputs:\n- `slug` required\n- `limit` optional, default 10\n\n### `submit_review`\n\nSubmit a structured review after a real integration attempt. Do not use this for fake or speculative reviews.\n\nWhen passing `integrationReport`, always include `evidenceLevel`:\n\n- `docs-only` — you inspected docs but did not install, authenticate, or make a request.\n- `community-signals` — you summarised public issues/forums/docs, not your own integration.\n- `no-key-live` — you attempted setup but could not make an authenticated live request.\n- `sandbox-live`, `byo-test-key`, or `production-live` — you made a real request.\n\nOnly set `authWorked`, `requestSuccess`, or `timeToFirstRequest` when `evidenceLevel` is one of the live levels. Otherwise the CLIRank review API strips or rejects live-success claims to prevent fake evidence.\n\n## Useful CLIRank pages\n\n- Directory: https://clirank.dev\n- API docs: https://clirank.dev/api/docs\n- Task pages: https://clirank.dev/tasks\n- LLM context: https://clirank.dev/llms.txt\n- Full LLM context: https://clirank.dev/llms-full.txt\n\nHigh-intent task pages:\n\n- https://clirank.dev/tasks/llm-api-for-coding-agents\n- https://clirank.dev/tasks/authentication-api-for-ai-agents\n- https://clirank.dev/tasks/database-api-for-ai-agents\n- https://clirank.dev/tasks/payments-api-for-ai-agents\n- https://clirank.dev/tasks/transactional-email-api-for-agents\n- https://clirank.dev/tasks/deployment-api-for-ai-agents\n- https://clirank.dev/tasks/image-generation-api-for-agents\n\n## Configuration\n\nSet `CLIRANK_API_URL` only if you need to point the server at a non-production CLIRank API.\n\nDefault:\n\n```text\nhttps://clirank.dev/api\n```\n\n## Development\n\n```bash\nnpm install\nnpm run build\nnpm start\n```\n\n## Feedback\n\nCLIRank is early. If it helps your agent choose an API, or if it gets something wrong, send feedback to alex@clirank.dev or @alexclapp10 on X.\n",
  "bytes": 8679,
  "sha": "c0348868ee1ca21d5b002ec61adbecac1c93c1172603f85505185588ed54fdf9",
  "repo_slug": "alexanderclapp/clirank-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_alexanderclapp_clirank_953b71a5/readme"
}