browse_categories
List all API categories in the CLIRank directory with the number of APIs in each.
LABSCO SUMMARY
A decision step before integration code, with the evidence rules built into the write path.
The review side is what keeps the data honest: submit_review demands an evidenceLevel, and the API refuses live-success fields on a docs-only report — so a score cannot be inflated by an agent that never made a request. The read side earns its place through get_api_docs, which returns the exact auth header and env var name rather than a link to go read.
What it is
An MCP server over the CLIRank directory, meant to be called before an agent installs an SDK or writes integration code. It answers which API fits a task with present-day pricing, auth method and headless-CLI signals, rather than leaving the choice to model memory or a broad web search.
What you get
- discover_apis — search by intent, filtered by minimum CLI relevance score and pricing model (free, freemium, paid, pay-per-use or transaction-based)
- recommend — one opinionated pick for a concrete task, with the runner-up and the reasoning
- get_api_details — scores, pricing, auth method, capabilities and quality breakdown for one API by slug
- get_api_docs — an agent-shaped quickstart: current base URL, the exact auth header, the environment variable name, the SDK install command and an init snippet
- compare_apis — two to five APIs side by side on score, pricing, auth and capabilities
- browse_categories and get_reviews — the category list with counts, and integration reports from humans and agents
- submit_review — a structured report after a real attempt; evidenceLevel is required, and live-success claims are stripped unless the level says a real request was made
Requirements
Nothing — clients run npx -y clirank-mcp-server@latest over stdio and it talks to https://clirank.dev/api with no CLIRank key. There is also a hosted endpoint at https://clirank-mcp.fly.dev/mcp for clients that speak remote MCP. Set CLIRANK_API_URL only to point at a non-production API.
Setup effort
One command — npx -y clirank-mcp-server@latest
USE CASES
01
Choosing an API for a concrete job
Ask for one recommendation with the runner-up, then read the docs for the winner before writing code.
02
Exploring the options first
Search by what you need, filter by pricing model, then put the finalists side by side.
03
Checking an API before committing
Read its scores and auth method, then what other integrators reported.
04
Closing the loop after an integration
File what actually happened at the right evidence level, successful or not.
05
Confirming a package is current
Check the version, compatibility and deprecation state before you install it.
9 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
compare_apis
Compare two or more APIs side by side. Returns a comparison table with scores, pricing, auth, and capabilities.
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.
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.
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.
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.
BEFORE YOU INSTALL
What to know first
Tools you get
9 tools when we connected.
Requires
npx on PATH
CONTEXT COST
Light Standing cost
Rated by the size of the 9 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"clirank-mcp-server": {
"command": "npx",
"args": [
"-y",
"clirank-mcp-server@latest"
]
}
}
}npx
TERMINAL
npx -y clirank-mcp-server@latest
