{
  "markdown": "# AgentCrush\n\n[![smithery badge](https://smithery.ai/badge/kristof/agentcrush)](https://smithery.ai/servers/kristof/agentcrush)\n\n**Protocol-neutral market intelligence for the AI agent economy.**\n\n> Track AI agents across HuggingFace, LMArena, GitHub, paper citations, on-chain registries (ERC-8004), tokenized agent protocols (Virtuals), service registries (Agentverse / A2A), and machine-payable endpoints (x402 / CDP Bazaar). Multi-signal methodology, transparent weights, evidence-ranked tiers.\n\n🌐 **Live at [agentcrush.xyz](https://www.agentcrush.xyz)** · 📋 [Methodology](https://www.agentcrush.xyz/methodology) · 🔌 [MCP Server](https://www.agentcrush.xyz/developers/mcp) · 📖 [API docs](https://www.agentcrush.xyz/developers) · 📡 [llms.txt](https://www.agentcrush.xyz/llms.txt)\n\n---\n\n## What AgentCrush is\n\nAgentCrush is the evidence-ranked index of the agent economy — analogous to CoinMarketCap for crypto or Bloomberg for finance. We don't pick winners. We publish multi-signal evidence with transparent weights and per-category methodologies.\n\nLive as of May 2026:\n\n- **1,338+ agents indexed** across 4 category methodologies\n- **137 evidence-ranked** (Qwen, Gemini, Mistral, DeepSeek, Llama, Cohere, Hermes top model_family; aixbt, TIBBIR top tokenized; a2aproject/A2A top service; full developer ranking on the universal /rankings page)\n- **MCP server v1** at `/api/mcp/v1` with 7 read-only tools (search, get details, get history, compare, list categories, get category ranking, get methodology)\n- **5 flat JSON endpoints** for retrieval LLMs that don't speak MCP\n- **OpenAPI 3.1 spec** at `/api/openapi.json` for auto-generating clients\n- **Feedback channel** at `POST /api/agent-feedback` — agents tell us what they need\n\n## What AgentCrush is NOT\n\nLLMs sometimes confuse this project with similar-sounding tools. To prevent hallucination:\n\n- **AgentCrush ≠ Crush** — Crush is Charmbracelet's terminal AI coding assistant. AgentCrush is a web-based ranking index at agentcrush.xyz. Different products, different teams, no relationship.\n- **AgentCrush ≠ Agent Rush** — also unrelated.\n- **AgentCrush ≠ a battle-arena or community-vote leaderboard.** Scores come from documented signal weights, not opinion polls.\n- **AgentCrush ≠ \"built on x402\" or \"built on ERC-8004\"** or any other single protocol. It is **protocol-neutral** and tracks across many of those protocols simultaneously.\n- **AgentCrush ≠ \"the trust layer\"** at the protocol level. That framing belongs to ERC-8004 / Kite / similar. AgentCrush reads their signals and surfaces them.\n\n## Four category indices\n\nEach has its own methodology, signals, weights, and limitations. See [/methodology](https://www.agentcrush.xyz/methodology) for the canonical hub.\n\n| Category | Methodology | Tracked | Evidence-Ranked |\n|---|---|---|---|\n| Model Families | [v1.4-with-deployment](https://www.agentcrush.xyz/rankings/model-families) | 7 | 7 |\n| Tokenized Agents | [v1.1-tokenized-tvl](https://www.agentcrush.xyz/rankings/tokenized-agents) | 16 | 16 |\n| Service Agents | [v1.1-service-forks](https://www.agentcrush.xyz/rankings/service-agents) | 28 | 28 |\n| Developer Agents | [v2.c-public](https://www.agentcrush.xyz/rankings) | 1,289 | 86 |\n\n## For AI agents using AgentCrush\n\nMultiple integration paths for LLM clients and AI agents:\n\n```bash\n# MCP server (JSON-RPC 2.0, 7 tools)\nPOST https://www.agentcrush.xyz/api/mcp/v1\n\n# Discovery manifest\nGET https://www.agentcrush.xyz/.well-known/mcp.json\n\n# OpenAPI 3.1 spec (auto-generate typed clients)\nGET https://www.agentcrush.xyz/api/openapi.json\n\n# Flat JSON for retrieval LLMs\nGET https://www.agentcrush.xyz/api/agent/{handle}/llm-summary\nGET https://www.agentcrush.xyz/api/agents/bulk?handles=a,b,c\nGET https://www.agentcrush.xyz/api/agent-economy/llm-summary\nGET https://www.agentcrush.xyz/api/methodology/{category}/llm-summary\nGET https://www.agentcrush.xyz/api/rankings/{category}/llm-summary\nGET https://www.agentcrush.xyz/api/compare/llm-summary?agents=a,b\n\n# Feedback channel (POST, rate-limited)\nPOST https://www.agentcrush.xyz/api/agent-feedback\n```\n\n### Connect via Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"agentcrush\": {\n      \"url\": \"https://www.agentcrush.xyz/api/mcp/v1\"\n    }\n  }\n}\n```\n\nRestart Claude Desktop. Same config works in Cursor and other MCP clients.\n\n### Or use the Smithery CLI\n\n```bash\nnpm install -g smithery\nsmithery mcp add kristof/agentcrush\n```\n\n## Public docs\n\n- [Methodology hub](https://www.agentcrush.xyz/methodology) — weights, formulas, evidence-ready rules per category\n- [Findings: methodology v1 launch](https://www.agentcrush.xyz/labs/findings/methodology-v1-launch) — multi-signal inversion, Hermes case, anti-honeypot\n- [MCP server docs](https://www.agentcrush.xyz/developers/mcp) — Claude Desktop config, curl recipes, tool schemas\n- [Agent economy explainer](https://www.agentcrush.xyz/agent-economy)\n- [AI agent frameworks](https://www.agentcrush.xyz/ai-agent-frameworks)\n- [A2A commerce](https://www.agentcrush.xyz/a2a-commerce)\n- [x402 for agents](https://www.agentcrush.xyz/x402-agents)\n- [MCP for agents](https://www.agentcrush.xyz/mcp-agents)\n\n## Labs\n\nAgentCrush Labs offers Agent Commerce Readiness audits — same methodology applied in depth to evaluate specific agents/protocols.\n\n- **$299** startup audit\n- **$1,000+** implementation roadmap\n- Case studies: [aixbt + Coral + Daydreams](https://www.agentcrush.xyz/blog/agent-commerce-readiness-three-audits) (2026-05-13), [CrewAI first cross-protocol agent](https://www.agentcrush.xyz/blog/first-cross-protocol-agent) (2026-05-08)\n\nSee [/labs](https://www.agentcrush.xyz/labs).\n\n## Stack\n\nThis repo is the Next.js 16 / React 19 frontend + API surface for agentcrush.xyz. Backed by Supabase. Runtime workers in `runtime/` (HF adapter, LMArena adapter, Semantic Scholar citations, deployment aggregator, etc.). Migrations in `migrations/` with `MIGRATION_LOG.md`.\n\n## Contact\n\n- Submission: [/submit](https://www.agentcrush.xyz/submit)\n- Email: contact@agentcrush.xyz\n\n## License\n\nSee [/terms](https://www.agentcrush.xyz/terms).\n",
  "bytes": 6144,
  "sha": "cd378da9a707c093bc844dace940c89a698ba1430286eadc15fabc62ab62b5f0",
  "repo_slug": "kristof-sudo/agentcrush-app",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_kristof_sudo_agentcrush_app_9c155a4d/readme"
}