EvalGate
OnlineNewRun AI evaluations, record agent traces and gate releases on evidence, with scoped org access.
What it can do: 17 tools
project_inspectread-onlySnapshot the evaluations and project keys in the authenticated organization. Use it first to orient in an unfamiliar workspace or to resolve a projectKey. Returns evaluation summaries, a bounded count and a web link; chaproject_planread-onlyPlan the next steps for connecting a repository, reviewing an evaluation, or ingesting traces. Use it when deciding what to set up next. Returns an ordered advisory step list and a web link; it never runs, writes or acceevaluations_listread-onlyList the organization's evaluations, optionally filtered by lifecycle status. Use it to find an evaluationId before calling runs_list or baseline_lineage. Returns one page of evaluation summaries and a nextCursor for theruns_listread-onlyList the runs of one evaluation, newest first, optionally filtered by status. Use it to find a runId or check recent results and regression signals. Returns one page of run summaries and a nextCursor for the following parun_explainread-onlyExplain why one run passed or failed. Use it after runs_list when you need the failing cases and where the evidence came from. Returns the run's status, its failed cases with result metadata, an evidence-lineage summary,baseline_lineageread-onlyShow which run is the published baseline for an evaluation and where its evidence came from. Use it before comparing a new run against the baseline. Returns the baseline run and version, a lineage summary, or not_found.docs_searchread-onlySearch EvalGate's public REST API operations by keyword. Use it to find the right endpoint before writing an API call. Returns matching operations with method, path, summary and operationId; for product guides use the doconnector_healthread-onlyShow the latest persisted connector-readiness reports, optionally for one connector. Use it to check whether an integration was set up and scored. Returns each report's status, score and timestamp; it is not a live credeconnections_listread-onlyList the workspace's current connections with their source restrictions and freshness. Use it to see what is already connected before planning a new one. Returns connection metadata and a continuation cursor; never secreconnections_catalogread-onlyInspect every connector definition and its exact installed setup path. Use it to choose a connector or find how to install one. Returns connector definitions with setup paths; blueprints that are unavailable and live verconnections_rootsread-onlyPage through the configured account roots (top-level connected accounts) using current administrator authority. Use it to audit which accounts are configured. Returns root metadata and a continuation cursor; never secretconnections_graphread-onlyRead how connections link to resources: canonical connection references and the exact resource revisions currently visible. Use it to trace which source revision a connection points at. Returns references and revisions;quality_contexts_listread-onlyList Portable Quality work contexts visible to the authenticated principal.quality_resources_listread-onlyList the immutable resource revisions currently attached to a visible Portable Quality context.quality_plans_listread-onlyList frozen Portable Quality plans visible to the authenticated principal.quality_check_getread-onlyGet one Portable Quality execution owned by the authenticated principal.quality_standards_resolveread-onlyResolve approved Portable Quality standards for the authenticated principal and exact task scope.
Connect it
claude mcp add --transport http evalgate https://www.evalgate.com/api/mcpSettings → Connectors → Add custom connector
URL: https://www.evalgate.com/api/mcp{
"mcpServers": {
"evalgate": {
"url": "https://www.evalgate.com/api/mcp"
}
}
}{
"servers": {
"evalgate": {
"type": "http",
"url": "https://www.evalgate.com/api/mcp"
}
}
}Questions
What does EvalGate do?
Run AI evaluations, record agent traces and gate releases on evidence, with scoped org access. It exposes 17 tools to AI assistants.
What tools does EvalGate provide?
17 tools, including project_inspect, project_plan, evaluations_list, runs_list, run_explain, baseline_lineage, docs_search, connector_health, connections_list, connections_catalog, connections_roots, connections_graph….
How do I connect EvalGate to Claude, ChatGPT or Cursor?
Add the remote MCP endpoint https://www.evalgate.com/api/mcp as a custom connector or MCP server. Copy-paste setup is on this page.
Does EvalGate require an account or API key?
No sign-in was needed to list its tools. Individual tools may still need an account or API key.
Is EvalGate online?
As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.
Who publishes EvalGate?
evalgate.com. The official MCP Registry verified that the publisher controls this domain before accepting the listing.
Similar in Project Management
-
SanityOnline · sign-in requiredPopular
Gives AI agents direct access to your Sanity projects and guidance for working with them
-
LinearOnline · sign-in requiredOfficialPopular
Find and manage issues, projects, and documents in your Linear workspace.
-
ReqResOnlineOfficial
Hosted backend for AI agents: create projects with persistent collections and keys, no signup.
-
ChainstackOnlineOfficial
Deploy and manage blockchain nodes across 70+ protocols, search docs, request testnet funds.
-
Singularity AppOnline · sign-in requiredOfficialNew
Manage tasks, projects, habits, Kanban boards, and time tracking with SingularityApp.
-
Release AlertOnlineOfficialNew
Connect AI assistants to Release Alert.