{
  "markdown": "# Hlido MCP Server\n\n[![smithery badge](https://smithery.ai/badge/ankitkapur1992/hlido)](https://smithery.ai/server/ankitkapur1992/hlido)\n\n**Independent trust scores, claim audits, and comparisons for AI agents — queryable by your agent over [MCP](https://modelcontextprotocol.io).**\n\n[Hlido](https://hlido.eu) is an independent AI-agent review platform (\"Rotten Tomatoes for AI agents\"). We test agents hands-on and publish evidence-backed scorecards: a 0–100 score, tier verdict, per-claim PASS/FAIL audit, and signed screenshots. This repository contains the source of the MCP server that exposes that registry to other agents.\n\n## Use the hosted server (no install)\n\nThe server runs as a Cloudflare Worker at:\n\n```\nhttps://hlido.eu/mcp\n```\n\n**Claude Code:**\n```bash\nclaude mcp add --transport http hlido https://hlido.eu/mcp\n```\n\n**Claude Desktop / Cursor / any MCP client** (`mcpServers` config):\n```json\n{\n  \"mcpServers\": {\n    \"hlido\": { \"url\": \"https://hlido.eu/mcp\" }\n  }\n}\n```\n\nAlso listed on [Smithery](https://smithery.ai/server/ankitkapur1992/hlido) and mcp.so.\n\n## Tools\n\n| Tool | What it answers |\n|---|---|\n| `trust_check` | \"Is agent X trustworthy?\" — score, tier, verdict for a slug |\n| `find_trusted` | \"Find me a trusted agent for <need>\" — filtered registry search |\n| `verify_claim` | \"Does X really do Y?\" — per-claim PASS/FAIL evidence |\n| `compare_agents` | Side-by-side scorecard comparison |\n| `get_scorecard` | Full sanitized scorecard JSON for a slug |\n| `find_similar_agents` | Semantic nearest neighbours to a given agent |\n| `submit_agent` | Nominate an agent for review |\n| `report_review_issue` | Flag a problem with a published review |\n| `request_quick_audit` | Ask for a fast re-check of a stale review |\n\n(plus discovery/metadata tools — see `src/index.mjs` for the live tool table)\n\n## Design principles\n\n- **Public data only.** The server reads the same JSON published at `hlido.eu/data/*` (registry, scorecards, attestations). It never exposes scoring weights, grader assertions, or editorial drafts — the methodology stays private; the outcomes and evidence are public.\n- **No auth, no tracking.** Anonymous JSON-RPC. Lightweight daily per-tool counters are the only telemetry.\n- **Thin by intent.** This is an adapter over open data. The review pipeline, testing engine, and scoring model live elsewhere and are not part of this repository.\n\n## Self-hosting\n\nIt's a standard Cloudflare Worker. Copy `wrangler.toml.example` to `wrangler.toml`, set your account id, and `npx wrangler deploy`. Optional bindings (KV cache, Vectorize similarity index) degrade gracefully when absent — the worker falls back to fetching the public JSON directly.\n\n## Data & licensing\n\n- Code: [Apache-2.0](LICENSE)\n- Review data: [CC-BY](https://github.com/ankitkapur1992-hlido/hlido-public) via the public data mirror and the [HF dataset](https://huggingface.co/datasets/hlido-eu/agent-benchmark)\n\n## Links\n\n- Website: https://hlido.eu\n- Agent manifest: https://hlido.eu/agent-manifest.json\n- llms.txt: https://hlido.eu/llms.txt\n- Public data mirror: https://github.com/ankitkapur1992-hlido/hlido-public\n\n## Run with Docker\n\n```bash\ndocker build -t hlido-mcp .\ndocker run -p 8080:8080 hlido-mcp\n```\n\nThe container runs the worker on the local [workerd](https://github.com/cloudflare/workerd) runtime via `wrangler dev` — no Cloudflare account needed. The MCP endpoint is `http://localhost:8080/` (GET for server info, POST for JSON-RPC).\n",
  "bytes": 3459,
  "sha": "4d986156b62da374abaaa478ed877210430a873cbc99b6cff9529128b9b66acf",
  "repo_slug": "ankitkapur1992-hlido/hlido-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_eu_hlido_mcp_a651be3a/readme"
}