About Hlido Agent Reviews
Hlido Agent Reviews is an MCP server for agents that need evidence-backed assessments of AI agents. It exposes public scorecards and review tools while keeping the scoring methodology private.
Key features
- 01Agent trust scores and verdicts
- 02Per-claim evidence checks
- 03Scorecard comparisons
- 04Search and similarity discovery
- 05Review nominations and issue reports
Use cases
- 01Check an agent before adopting it
- 02Verify an agent capability claim
- 03Compare reviewed agents
- 04Nominate an agent or flag a review
MCP support
Provides MCP tools to query Hlido’s public review registry, including trust checks, claim verification, comparisons, and review submissions.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://hlido.eu/mcpclaude mcp add --transport http eu-hlido https://hlido.eu/mcp{"mcpServers":{"eu-hlido":{"type":"http","url":"https://hlido.eu/mcp"}}}Open in Cursor{"servers":{"eu-hlido":{"type":"http","url":"https://hlido.eu/mcp"}}}Open in VS Code{"mcpServers":{"eu-hlido":{"type":"http","url":"https://hlido.eu/mcp"}}}{"mcpServers":{"eu-hlido":{"serverUrl":"https://hlido.eu/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
19| Parameter | Type | Required | Description |
|---|---|---|---|
| use_case | string | No | Optional. The task you're considering this agent for (e.g. 'multi-file TypeScript refactor'); tailors the verdict to that use case when provided. |
| agent_or_url | string | Yes | The agent to check: either its Hlido slug (e.g. 'aider', 'cursor') or its product/homepage URL (e.g. 'https://cursor.com'). A URL is matched to the closest reviewed agent. |
Details
From the project READMEHlido MCP Server
Independent trust scores, claim audits, and comparisons for AI agents — queryable by your agent over MCP.
Hlido 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.
Use the hosted server (no install)
The server runs as a Cloudflare Worker at:
https://hlido.eu/mcp
Claude Code:
claude mcp add --transport http hlido https://hlido.eu/mcp
Claude Desktop / Cursor / any MCP client (mcpServers config):
{
"mcpServers": {
"hlido": { "url": "https://hlido.eu/mcp" }
}
}
Also listed on Smithery and mcp.so.
Tools
| Tool | What it answers |
|---|---|
trust_check | "Is agent X trustworthy?" — score, tier, verdict for a slug |
find_trusted | "Find me a trusted agent for " — filtered registry search |
verify_claim | "Does X really do Y?" — per-claim PASS/FAIL evidence |
compare_agents | Side-by-side scorecard comparison |
get_scorecard | Full sanitized scorecard JSON for a slug |
find_similar_agents | Semantic nearest neighbours to a given agent |
submit_agent | Nominate an agent for review |
report_review_issue | Flag a problem with a published review |
request_quick_audit | Ask for a fast re-check of a stale review |
(plus discovery/metadata tools — see src/index.mjs for the live tool table)
Design principles
- 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. - No auth, no tracking. Anonymous JSON-RPC. Lightweight daily per-tool counters are the only telemetry.
- 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.
Self-hosting
It'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.
Data & licensing
- Code: Apache-2.0
- Review data: CC-BY via the public data mirror and the HF dataset
Links
- Website: https://hlido.eu
- Agent manifest: https://hlido.eu/agent-manifest.json
- llms.txt: https://hlido.eu/llms.txt
- Public data mirror: https://github.com/ankitkapur1992-hlido/hlido-public
Run with Docker
docker build -t hlido-mcp .
docker run -p 8080:8080 hlido-mcp
The container runs the worker on the local workerd runtime via wrangler dev — no Cloudflare account needed. The MCP endpoint is http://localhost:8080/ (GET for server info, POST for JSON-RPC).
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.