EvalGate MCP Server

by evalgate Your server? Claim it

answering

EvalGate is answering right now. Last checked 1 min ago. It exposes 12 tools.

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

Uptime history 47 hours of history

47 hours agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

698 ms

Response time

average over 24h

open, no key

Access

streamable-http

Nothing serious here today

Today is the operative word: we check EvalGate every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add evalgate --transport http https://www.evalgate.com/api/mcp

Settings → Connectors → Add custom connector, then paste this address

https://www.evalgate.com/api/mcp

~/.codex/config.toml

[mcp_servers.evalgate]
url = "https://www.evalgate.com/api/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "evalgate": {
      "url": "https://www.evalgate.com/api/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "evalgate": {
      "type": "http",
      "url": "https://www.evalgate.com/api/mcp"
    }
  }
}

Available tools 12

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

connections

connections_catalog

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

connections_graph

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

connections_list

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

connections_roots

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

project

project_inspect

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

project_plan

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

baseline

baseline_lineage

Show the published baseline anchor and its evidence lineage.

connector

connector_health

Show the latest connector-readiness reports for the organization.

docs

docs_search

Search the published OpenAPI operation catalog for relevant help.

evaluations

evaluations_list

List evaluations with a stable cursor for the organization.

explain

run_explain

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

runs

runs_list

List evaluation runs with stable cursors and regression signals.

Endpoints

URL	Transport	State	Latency	Checked
https://www.evalgate.com/api/mcp	streamable-http	answering	1783 ms	1 min ago

Alternatives to EvalGate

same job, measured the same way

EvalGate

by evalgate

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

12 tools answering

Context

by everydaysecurity

OSINT investigations with traceable evidence: domains, URLs, IPs, scams and business records.

answering

Tracelane MCP

by tracelane

Read-only, tenant-scoped access to Tracelane agent traces and guardrail verdicts

44 installs/wk local only

AxenomIA AX-SCI-001 — Scientific Novelty & Evidence

by perlita2013

Traceable scientific novelty and evidence assessment with source-linked results and a human gate.

3 tools answering

Infraveil Agent Guard

by infraveilhq

Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.

2 installs/wk local only

CiteNexus

by akougkas

Search scholarly sources, verify references, and export citations with traceable evidence.

134 installs/wk local only

AccordTrace

by kosta1985

Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.

9 tools answering

Noveum

by noveum

Trace, evaluate, and optimize your LLM, RAG, and agent apps with Noveum observability.

answering

EvalGate — questions

Answers built from our own checks of this server.

What can EvalGate do?

It exposes 12 tools, read directly from the server on our last check. Among them: baseline_lineage, connections_catalog, connections_graph, connections_list, connections_roots, connector_health and 6 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

What is EvalGate mostly used for?

Its tools cluster around connections and project. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.

Is EvalGate working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 698 ms. The bar chart above shows every period we have measured.

How do I connect EvalGate?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does EvalGate need an API key?

No. EvalGate completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 12 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is EvalGate?

It answers our handshake in 698 ms on average, which is faster than 12% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.