AgentCrush

Market intelligence for the AI agent economy: rankings, trust signals, liveness. 13 tools.

What does this entry provide?

AgentCrush is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 67/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding AgentCrush to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.

Snapshot facts

Source: Official MCP Registry
Quality: 67/100
Install method: streamable-http
Repo: kristof-sudo/agentcrush-app
Repo updated: Jun 12, 2026

Install command

mcp add io.github.kristof-sudo/agentcrush-app https://www.agentcrush.xyz/api/mcp/v1

Install method: streamable-http

Review the upstream source before running this command.

GitHub project Homepage

Quality

Repo stars

Repo updated

Jun 12, 2026

How is this score calculated?

Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.

MCP manifest

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-06-12T08:22:24.7666Z",
      "publishedAt": "2026-06-12T08:22:24.7666Z",
      "statusChangedAt": "2026-06-12T08:22:24.7666Z"
    }
  },
  "server": {
    "name": "io.github.kristof-sudo/agentcrush-app",
    "_meta": {
      "io.modelcontextprotocol.registry/publisher-provided": {
        "auth": "none",
        "tools": [
          "search_agents",
          "get_agent_details",
          "get_agent_history",
          "compare_agents",
          "list_categories",
          "get_category_ranking",
          "get_methodology",
          "get_agent_trust",
          "get_top_movers",
          "get_protocol_adoption",
          "get_agent_changes",
          "get_ecosystem_summary"
        ],
        "docs_url": "https://www.agentcrush.xyz/developers/mcp",
        "llms_txt": "https://www.agentcrush.xyz/llms.txt",
        "use_cases": [
          "User asks about a specific AI agent (CrewAI, LangGraph, Qwen, Gemini, etc.) — call get_agent_details",
          "User asks 'best AI agent for X' — call get_category_ranking or search_agents with category filter",
          "User compares two agents — call compare_agents or retrieve the comparison page",
          "User asks how a ranking is calculated — call get_methodology(category)",
          "Agent needs delegation decision — call get_agent_trust for trust score + classification",
          "Agent needs ecosystem-level state — call get_ecosystem_summary or get_protocol_adoption",
          "User asks what changed recently — call get_top_movers or get_agent_changes"
        ],
        "categories": [
          "data",
          "intelligence",
          "directory",
          "agent-economy",
          "ai-agents"
        ],
        "rate_limit": "60 requests/minute per IP",
        "openapi_spec": "https://www.agentcrush.xyz/api/openapi.json",
        "methodology_url": "https://www.agentcrush.xyz/methodology",
        "discovery_manifest": "https://www.agentcrush.xyz/.well-known/mcp.json"
      }
    },
    "title": "AgentCrush",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "remotes": [
      {
        "url": "https://www.agentcrush.xyz/api/mcp/v1",
        "type": "streamable-http"
      }
    ],
    "version": "1.3.0",
    "repository": {
      "url": "https://github.com/kristof-sudo/agentcrush-app",
      "source": "github"
    },
    "websiteUrl": "https://www.agentcrush.xyz",
    "description": "Market intelligence for the AI agent economy: rankings, trust signals, liveness. 13 tools."
  }
}

Report an issue with this listing