eu.hlido/mcp — Model Context Protocol (MCP) Server

This MCP server, “eu.hlido/mcp,” exposes evidence-backed reviews and trust checks for AI agents. It provides queryable information from Hlido, including independent trust scores, claim audits, incident registry data, and recommendations. The server is implemented as an MCP server with a documented purpose of sharing agent evaluation results with other agents.

🛠️ Key Features

Independent AI-agent reviews
Trust checks and evidence scorecards (0–100 score)
Per-claim PASS/FAIL audits
Incident registry
Recommendations
Tool count: 17

🚀 Use Cases

Query AI-agent reviews over MCP
Compare agents using trust scores and tier verdicts
Validate specific claims via PASS/FAIL audit results
Review incident-related information

⚡ Developer Benefits

Integrates with Model Context Protocol (MCP)
Developer-accessible topics: ai-agents, cloudflare-workers, mcp, mcp-server, model-context-protocol, agent-evaluation, reviews, trust
Uses repository-based source content (“source of the MCP server”)

⚠️ Limitations

Source excerpt only partially describes server behavior; full tool/API details are not included here.

Hlido 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:

code

https://hlido.eu/mcp

Claude Code:

bash

claude mcp add --transport http hlido https://hlido.eu/mcp

Claude Desktop / Cursor / any MCP client (mcpServers config):

json

{
  "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

Run with Docker

bash

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).

agent_or_url	string	required	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.
use_case	string	optional	Optional. The task you're considering this agent for (e.g. 'multi-file TypeScript refactor'); tailors the verdict to that use case when provided.

need	string	required	Free-text description of the capability you need (e.g. 'CLI coding agent that edits multiple files at once').
min_tier	string	optional	Minimum trust tier to include (VITAL is strictest, FLATLINE allows all). Defaults to STEADY.
limit	integer	optional	Maximum number of agents to return (default 10).

agent	string	required	The agent's Hlido slug or product URL (e.g. 'cursor').
claim	string	required	The specific claim to verify, in plain language (e.g. 'works offline' or 'SOC 2 compliant').

url	string	required	The agent's product or homepage URL (e.g. 'https://example.com').
name	string	required	Human-readable agent name (e.g. 'Example Coder').
note	string	optional	Optional context: what the agent does, or why it's worth reviewing.
email	string	optional	Optional contact email for the submitter — if you want a reply or a heads-up when the review publishes. Providing it always flags the submission to the Hlido team.

slug	string	optional	Optional: only incidents for this agent slug
severity	string	optional	Optional minimum-interest filter (exact match)
category	string	optional	Optional category filter
limit	integer	optional	Max results (default 20, max 100)

Hlido Agent Reviews

eu.hlido/mcp — Model Context Protocol (MCP) Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

trust_check

find_trusted

verify_claim

compare_agents

submit_agent

verify_transparency

get_scorecard

get_incidents

report_review_issue

request_quick_audit

find_similar_agents

subscribe

explain

recommend

get_behavioral_trace

commerce_check

scan_mcp

Hlido MCP Server

Use the hosted server (no install)

Tools

Design principles

Self-hosting

Data & licensing

Links

Run with Docker

Install

Remote endpoint

Related servers

url	string	required	Homepage or product URL of the agent to audit
name	string	optional	Optional human-readable name (we'll derive from URL if missing)
why	string	optional	Optional one-liner: why are you considering this agent? helps us prioritize
requester	string	optional	Optional self-identifier — agent name, email, or session id — for rate-limiting + follow-up

description	string	required	Free-text description of the task or capability you need
top_k	integer	optional	Number of matches to return (default 5, max 20)
min_score	integer	optional	Minimum Laddoo score filter (default 0)

server	string	required	The MCP server to scan: an HTTP(S) MCP endpoint URL (e.g. 'https://mcp.example.com/mcp' — scanned live), OR an npm package (e.g. '@modelcontextprotocol/server-filesystem'), PyPI package, or GitHub repo URL (queued for sandbox scan).
requester	string	optional	Optional self-identifier — agent name or email — for follow-up when a queued scan completes.

slug	string	required	The Hlido slug to subscribe to (e.g. 'cursor', 'aider')
channel	string	optional	Preferred notification channel. webhook is advisory only until Wave 3 ships.

slug	string	required	The Hlido slug to fetch behavioral trace for (e.g. 'aider', 'opencode')
spec_version	string	optional	Behavioral spec version (default 'v0.1'). Omit to get the latest available.