EvalGate

io.github.evalgatePublished by GitHub account evalgatev1.0.0Updated Oct 26, 2026

Create and run AI evaluations, record traces, and inspect results with scoped organization access.

The publisher's own server: EvalGate

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

Remote EvalGate MCP server that lets an assistant inspect AI evaluations, runs, baselines and connector health for an organization.

What you can do
  • Inspect projects, evaluations and project keys in the authenticated organization, and get a non-mutating plan for connecting a repository, evaluation or trace source.
  • List evaluations and evaluation runs with stable cursors and regression signals.
  • Explain a run from its status, failed-case metadata and evidence lineage, and show the published baseline anchor with its lineage.
  • Search the published OpenAPI operation catalog for help.
  • Review connector readiness reports, workspace connection metadata, connector definitions and installed setup paths, configured account roots, and connection references with visible resource revisions.
When to use it
Useful when you work with EvalGate evaluations and want an assistant to summarize runs, investigate failures and regressions, check baselines, or review connector and connection setup without leaving the chat.
Requirements
A remote streamable HTTP endpoint at evalgate.com; no local package. Requires an EvalGate organization API key sent as a bearer token in the Authorization header.
Before you install
The API key is an organization credential sent in the Authorization header; keep it scoped and out of shared logs. Tools are described as read-only and non-mutating, but they expose organization metadata such as project keys, connection details and account roots to the assistant and its model provider.

Installation

In SourceWeft

  1. Open EvalGate in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.evalgate%2Fevalgate/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "evalgate": {
      "type": "http",
      "url": "https://www.evalgate.com/api/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

Tools

12

project.inspect

Inspect the evaluations and project keys available in the authenticated organization.

ParametersprojectKey

project.plan

Return a non-mutating next-step plan for connecting a repository, evaluation, or trace source.

Parameterstarget

evaluations.list

List evaluations with a stable cursor for the organization.

Parameterslimitcursorstatus

runs.list

List evaluation runs with stable cursors and regression signals.

ParameterslimitcursorstatusevaluationIdrequired

run.explain

Explain a run using its status, failed-case metadata, and evidence-lineage summary.

ParametersrunIdrequired

baseline.lineage

Show the published baseline anchor and its evidence lineage.

ParametersevaluationIdrequired

connector.health

Show the latest connector-readiness reports for the organization.

ParametersconnectorKey

connections.list

List current workspace connection metadata, with source restrictions, freshness and bounded continuation. Does not reveal secrets or grant source access.

Parametersqlimitcursorsource

connections.catalog

Inspect all connector definitions and exact installed setup paths. Unavailable blueprints and live verification are separate facts.

Takes no parameters.

connections.roots

Page independent configured account roots using current administrator authority. Does not list secrets or imply verified connector availability.

Parametersqlimitcursor

connections.graph

Read canonical connection references and currently visible exact resource revisions. No source access grant or execution.

Parametersidrequired

Version history

1
  1. v1.0.0LatestOct 18, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Evalgate integrations

EvalGate

com.evalgateOfficial publisher

EvalGate is a remote MCP server for inspecting AI evaluation projects, runs, baselines and connector health in an authenticated organization.

Streamable HTTPWeb executable
Developer Tools12 toolsNov 5, 2026

EvalGate Docs

com.evalgateOfficial publisher

Read-only remote MCP server that lets an assistant list, search and read EvalGate's published documentation pages.

Streamable HTTPWeb executable
Knowledge & Memory3 toolsNov 5, 2026

Evalgate

Published by GitHub account ipezygj

A local MCP server that runs statistical checks on AI evaluation results before an assistant treats a reported score as trustworthy.

STDIODesktop only
AI & MLNot validated yetOct 24, 2026