EvalGate

com.evalgate/evalgate · v1.0.0 · agents-and-memory

EvalGate is healthy: it completed an MCP handshake in 855 ms and exposes 12 tools.

Run AI evaluations, record agent traces and gate releases on evidence, with scoped org access.

Endpoint: https://www.evalgate.com/api/mcp (streamable-http)

No repository listed · Website · JSON · Add to my inventory

Facts

Users (last 30 days)0
HandshakeHealthy
Auth neededNone
Tool count12
Latency855 ms
Last checked (UTC)2026-11-05T08:55:44.213Z

Health history

Checked (UTC)StatusLatencyError
2026-11-05T08:55:44.213ZHealthy855

Tools (12)

project_inspectInspect the evaluations and project keys available in the authenticated organization.
project_planReturn a non-mutating next-step plan for connecting a repository, evaluation, or trace source.
evaluations_listList evaluations with a stable cursor for the organization.
runs_listList evaluation runs with stable cursors and regression signals.
run_explainExplain a run using its status, failed-case metadata, and evidence-lineage summary.
baseline_lineageShow the published baseline anchor and its evidence lineage.
docs_searchSearch the published OpenAPI operation catalog for relevant help.
connector_healthShow the latest connector-readiness reports for the organization.
connections_listList current workspace connection metadata, with source restrictions, freshness and bounded continuation. Does not reveal secrets or grant source access.
connections_catalogInspect all connector definitions and exact installed setup paths. Unavailable blueprints and live verification are separate facts.
connections_rootsPage independent configured account roots using current administrator authority. Does not list secrets or imply verified connector availability.
connections_graphRead canonical connection references and currently visible exact resource revisions. No source access grant or execution.