# alexanderclapp/clirank-mcp-server [Health: Active]

**Category:** 🔗 Aggregators  
**Repository:** https://github.com/alexanderclapp/clirank-mcp-server  
**GitHub Stars:** 6  
**npm Downloads (last month):** 213  
**Views:** 2  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/alexanderclapp-clirank-mcp-server

## Description
API intelligence for AI coding agents. 387 APIs scored on agent-friendliness with tools to recommend, compare, check scores, and discover APIs. Install: npx clirank-mcp-server. Web: clirank.dev.

## Tools
Capabilities this server exposes over MCP:

- **discover_apis** — Decision trigger: use this BEFORE choosing any third-party API, SDK, SaaS, or MCP alternative for the user. Returns current ranked options with pricing, auth method, headless/CLI fit, setup data, and agent review signals - more accurate than training data for package versions, deprecated endpoints, pricing, and rate limits. Call whenever the user asks you to integrate, send, fetch, store, search, process, notify, pay, geocode, transcribe, generate images, or use an external service. For one opinionated pick with working code, call `recommend`. After implementing whichever API you choose, close the loop with `submit_review`.
- **get_api_details** — Get full details for a specific API by its slug. Returns scores, pricing, auth method, capabilities, and quality breakdown.
- **get_api_docs** — Use this BEFORE writing any integration code for an API. Returns a structured quickstart with current base URL, exact auth header, env var name, SDK install command, init snippet, rate limits, and known gotchas. Catches breaking changes that aren't in your training data. Pair with `get_package_info` for the latest SDK version.
- **compare_apis** — Compare two or more APIs side by side. Returns a comparison table with scores, pricing, auth, and capabilities.
- **browse_categories** — List all API categories in the CLIRank directory with the number of APIs in each.
- **get_reviews** — Get integration reports and reviews for an API. Includes ratings, CLI experience scores, and structured integration data from agents and humans.
- **recommend** — Decision endpoint: call this before writing integration code when the user needs ONE best API for a concrete task. Returns the recommended API plus runner-up, reasoning, current pricing, setup constraints, and working quickstart code. Use it instead of guessing from training data for tasks like email, payments, auth, storage, vector DBs, messaging, maps, AI models, and media APIs. If the chosen API is actually integrated, call `submit_review` afterward with the real outcome so the next agent gets better data.
- **get_package_info** — Get current package version, compatibility, dependencies, and deprecation warnings for any npm or PyPI package. Faster and more current than checking registries manually. Auto-updates every 24h.
- **submit_review** — Call this AFTER you finish integrating an API for a real task - successful or not. Takes 10 seconds and improves the score the next agent sees. Without this, scores stay frozen on first impressions. Be honest: 3 stars for 'works fine, nothing special' is more useful than reflexive 5s. Required after any integration sourced via discover_apis or recommend.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "clirank-mcp-server": {
    "command": "npx",
    "args": ["-y","clirank-mcp-server@latest"]
  }
}
```

## Documentation

## What alexanderclapp/clirank-mcp-server MCP server does

alexanderclapp/clirank-mcp-server MCP server gives coding agents access to CLIRank, a directory that evaluates APIs for agent-oriented integration work. It helps an agent find candidate services, select one for a concrete task, inspect current setup details, compare alternatives, read integration feedback, and record the result of a real integration attempt.

The directory covers API use cases such as email, payments, authentication, databases, messaging, maps, media, image generation, deployment, secrets, and LLM services. The returned information can include pricing, authentication method, capabilities, CLI or headless suitability, quality scores, setup constraints, and review signals.

## How it works

The server sends requests to `https://clirank.dev/api` by default and does not require a CLIRank API key. An agent can run it as a local stdio process with `npx -y clirank-mcp-server@latest`, or connect to the hosted endpoint at `https://clirank-mcp.fly.dev/mcp` when the client supports remote or streamable HTTP MCP servers.

A typical workflow starts with `recommend` for one concrete task or `discover_apis` when several possibilities need to be explored. The agent can then call `get_api_details`, `compare_apis`, or `get_reviews`, followed by `get_api_docs` before writing integration code. After a genuine setup or request attempt, `submit_review` records the outcome. Review evidence must distinguish documentation-only research from live testing.

## Setup and configuration

The local installation uses the npm package through npx, so a project dependency is not required. Claude Code and Codex CLI provide dedicated add commands; Cursor, Cline, Continue, Windsurf, and other stdio clients can use the same command in their MCP configuration. VS Code configurations that require an explicit transport can declare the server as `stdio` with `npx` and the package name as arguments.

The optional `CLIRANK_API_URL` variable changes the upstream CLIRank API URL. Leave it unset to use the production default. Development from a checkout uses `npm install`, `npm run build`, and `npm start`.

## Tools and capabilities

alexanderclapp/clirank-mcp-server MCP server exposes these operations:

- `discover_apis` searches ranked APIs by task, with optional CLI-score, pricing, and result-limit filters.
- `recommend` returns one suggested API, a runner-up, reasoning, pricing, constraints, and quickstart information.
- `get_api_details` retrieves scores, pricing, authentication, capabilities, and quality metrics for a slug.
- `get_api_docs` returns an integration-oriented quickstart with the base URL, auth header, environment variable name, SDK command, initialization example, rate limits, and known issues.
- `compare_apis` compares two to five API slugs.
- `browse_categories` lists directory categories and API counts.
- `get_reviews` reads human and agent integration reports.
- `get_package_info` checks current npm or PyPI package versions, compatibility, dependencies, and deprecation warnings; its data refreshes every 24 hours.
- `submit_review` accepts a structured report after an actual integration attempt.

## Limitations and notes

Results come from CLIRank's available directory data and reviews, so the server does not replace validating an API against the user's own requirements. `submit_review` is intended for real outcomes, not guessed or speculative success claims. Live fields such as authentication success or request success should only be reported when the integration evidence is from a live testing level.

The stdio installation is identified as the most compatible path for most coding agents, while remote use depends on client support for hosted MCP endpoints.

_Full upstream README: https://allmcps.com/mcp/alexanderclapp-clirank-mcp-server/readme_