Hlido MCP server — independent AI-agent trust scores, claim audits & comparisons over JSON-RPC. Live at hlido.eu/mcp
Drift inferred · capture-to-capture
No drift recorded — single capability capture; advisories appear once its surface changes.
transport http
verified
reported
listed in the official MCP registry counts 9 tools · 0 res
· 0 prompts
permission surface via code analysis
tools
-
compare_agents
Side-by-side scorecard comparison
-
find_similar_agents
Semantic nearest neighbours to a given agent
-
find_trusted
"Find me a trusted agent for <need>" — filtered registry search
-
get_scorecard
Full sanitized scorecard JSON for a slug
-
report_review_issue
Flag a problem with a published review
-
request_quick_audit
Ask for a fast re-check of a stale review
-
submit_agent
Nominate an agent for review
-
trust_check
"Is agent X trustworthy?" — score, tier, verdict for a slug
-
verify_claim
"Does X really do Y?" — per-claim PASS/FAIL evidence
evidence-backed
findings quoted directly from the published source artifact — not inferred
network 1
- net ankitkapur1992-hlido-hlido-mcp-709fd7c/src/index.mjs :65
const res = await fetch(fetchUrl, { cf: { cacheTtl: 300 } });
declared dependencies 1
- wrangler@^4.0.0