Docs / Reference / MCP server

MCP server — tool reference

Endpoint: https://hlido.eu/mcp — JSON-RPC 2.0 (Streamable HTTP). No authentication for read tools. Listed on the Official MCP Registry, Smithery, mcp.so and Glama.

Add to your client#

{
  "mcpServers": {
    "hlido": { "url": "https://hlido.eu/mcp" }
  }
}

Works in Claude Code (claude mcp add --transport http hlido https://hlido.eu/mcp), Cursor, Cline, Continue, Goose — any MCP-capable client.

Tool reference#

ToolArgumentsReturns
trust_checkslugOne-call trust summary: score, tier, headline verdict, staleness.
find_trustedneed (free text)Ranked reviewed agents matching a capability need.
verify_claimslug, claimWhether Hlido has independently tested that specific claim, with evidence.
compare_agentsslugs[] (≤5)Side-by-side scores, tiers, strengths and failure modes.
get_scorecardslugFull v2 scorecard — see the schema reference.
explainslugStructured why-this-tier breakdown.
recommendconstraints objectConstraint-driven shortlist (category, must-have surfaces, min score).
find_similar_agentstaskSemantic matches across the corpus.
get_incidentsslug?Published reliability incidents.
get_behavioral_traceslugVerified behavioral test runs where available.
commerce_checkslugAgentic-Commerce Readiness signals (interface surface, delegation safety).
submit_agenturl, name?Queues an agent for independent review (free).
report_review_issueslug, issueFiles a correction ticket against a review.
request_quick_auditurlRequests a fast surface audit (rate-limited per requester per day).
subscribeslug, contactChange alerts for an agent's score.

Example call#

curl -s https://hlido.eu/mcp -X POST -H 'content-type: application/json' -d '{
  "jsonrpc": "2.0", "id": 1, "method": "tools/call",
  "params": { "name": "trust_check", "arguments": { "slug": "aider" } }
}'

MCP vs raw JSON#

Use MCP when an agent decides at runtime (intent-shaped tools, no schema knowledge needed). Use the data endpoints when you want bulk data, caching control, or zero protocol overhead.