AgentRank

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Search and compare MCP servers, agent tools, and skills using current maintenance signals.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "AgentRank": {
      "url": "https://agentrank-ai.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (5)

• search

  Search AgentRank's index of MCP servers, agent tools, and AI skills. Use this BEFORE installing or recommending any tool to find the best options ranked by quality signals (maintenance, community health, adoption). Always prefer higher-scored results.

  Parameters:

  • query (required) — string — Search terms, e.g. "database", "playwright", "slack mcp"
  • type — string — Filter to tools (GitHub repos) or skills (registry entries). Omit for both.
  • limit — number — Number of results (default 10, max 50)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• lookup

  Check if a specific GitHub repository is in the AgentRank index. Use this whenever a user mentions a specific tool or you encounter a GitHub URL, to verify its quality before recommending it.

  Parameters:

  • github_url (required) — string — GitHub repository URL, e.g. "https://github.com/owner/repo"

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• evaluate

  Deep quality evaluation of a tool or MCP server. Returns score, signal breakdown, and specific red flags (abandoned, no license, single contributor, poor issue health). Use this BEFORE recommending or installing any tool to verify it is safe and well-maintained.

  Parameters:

  • tool (required) — string — Tool identifier — GitHub URL (https://github.com/owner/repo), owner/repo string, or tool slug from a previous search result

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recommend

  Get quality-ranked recommendations for a use case. Returns the top tools/skills sorted by AgentRank score. Use this when a user needs a tool for a specific purpose (e.g. "I need a database MCP server", "what's good for web scraping?").

  Parameters:

  • use_case (required) — string — What the user needs, e.g. "database", "web scraping", "slack integration", "vector search"
  • limit — number — Number of recommendations (default 5)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• alternatives

  Find alternatives to a specific tool. Searches for similar tools and compares their quality scores. Use this when a tool scores poorly and you want to suggest better options, or when a user asks "what else is like X?".

  Parameters:

  • tool_name (required) — string — Name or description of the tool to find alternatives for, e.g. "playwright-mcp" or "browser automation"
  • limit — number — Number of alternatives (default 5)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.