AgentRank MCP Server

1

Add it to Claude Code

Run this in a terminal.

Run in terminal
claude mcp add agentrank -- npx -y agentrank-mcp-server
README.md

Google PageRank for AI agents.

AgentRank

Google PageRank for AI agents. A live, daily-updated index of 25,000+ MCP servers and agent tools — scored by real GitHub signals, not just star counts.


Install in 3 Steps

1. Add to your AI tool:

# Claude Code
claude mcp add agentrank -- npx -y agentrank-mcp-server

2. Ask your AI to find a tool:

"Find me an MCP server for database access"

3. Get ranked, current results — automatically.

That's it. No API key, no config, no prompting. Your AI searches the live index whenever it needs a tool.

Cursor, VS Code, Cline, Claude Desktop, Windsurf →


Why AgentRank?

  • Your AI's knowledge is stale. Training data is months old — it can't know if a tool was abandoned last week or if something better shipped yesterday.
  • Stars lie. A repo with 2,000 stars and no commits in 18 months isn't production-ready. AgentRank weighs freshness, issue health, and dependents — not just popularity.
  • 25,000+ tools, scored daily. The index crawls GitHub nightly. Every recommendation reflects what's happening now.
  • Gets smarter with use. Every query surfaces which tools developers actually reach for, sharpening rankings for everyone.

Demo

> search("postgres mcp server")

1. postgres-mcp          Score: 91  ★ 2.1k  Updated: 2d ago
2. mcp-server-postgres   Score: 84  ★ 891   Updated: 5d ago
3. pg-mcp                Score: 71  ★ 432   Updated: 12d ago
> lookup("github.com/modelcontextprotocol/servers")

{
  "name": "modelcontextprotocol/servers",
  "agentrank_score": 97,
  "stars": 14200,
  "last_commit": "1 day ago",
  "dependents": 1840,
  "issue_health": 0.91
}

Links


Repo Structure

crawler/     GitHub crawler — finds and indexes repos nightly
scorer/      Scoring engine — 5-signal composite score (0-100)
mcp-server/  MCP server package published to npm
workers/     Cloudflare Workers API
site/        Astro frontend (agentrank-ai.com)

How the Score Works

Five signals, weighted by signal quality:

Signal Weight What it measures
Freshness 25% Days since last commit — stale repos decay fast
Issue health 25% Closed / total issues — maintainer responsiveness
Dependents 25% Repos that depend on this — real-world adoption
Stars 15% Raw popularity signal
Contributors 10% Bus factor — solo projects score lower

Scores are recomputed nightly from live GitHub data.


MIT License · Built by @comforteagle

Tools (2)

searchSearches the live index of MCP servers and agent tools based on a query.
lookupRetrieves detailed scoring and metadata for a specific repository.

Configuration

claude_desktop_config.json
{"mcpServers": {"agentrank": {"command": "npx", "args": ["-y", "agentrank-mcp-server"]}}}

Try it

Find me an MCP server for database access
Search for the best-ranked tools for web scraping
Lookup the AgentRank score and health metrics for github.com/modelcontextprotocol/servers
What are the top-rated MCP servers for file management?

Frequently Asked Questions

What are the key features of AgentRank?

Live, daily-updated index of over 25,000 MCP servers and agent tools. Scoring engine based on 5-signal composite score (freshness, issue health, dependents, stars, contributors). Real-time search capabilities for finding production-ready AI tools. Detailed repository metadata lookup including issue health and adoption metrics.

What can I use AgentRank for?

Finding reliable and actively maintained MCP servers for specific development tasks. Evaluating the production-readiness of an AI tool before integrating it. Discovering new, high-quality agent tools that have recently been released. Comparing multiple MCP servers for the same functionality based on objective health signals.

How do I install AgentRank?

Install AgentRank by running: claude mcp add agentrank -- npx -y agentrank-mcp-server

What MCP clients work with AgentRank?

AgentRank works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep AgentRank docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare