EvalGate

com.evalgate/evalgateevalgate.comstreamable-httpv1.0.0Scanned 2 hours ago

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

12 tools: 3 change things and 9 only read.

Reads private data · 2
Reads text others write · 0
Can send data out · 0
3 findings

Tools listed without sign-in. Remote posture

Anlyon alternative

3 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

12 tools

Changes things 3Creates or changes something that can be changed back.Claude Code: ask

connections_rootsPage independent configured account roots using current administrator authority.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Page independent configured account roots using current administrator authority. Does not list secrets or imply verified connector availability.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
run_explainExplain a run using its status, failed-case metadata, and evidence-lineage summary.1 finding
Why it is in this group
- The name "run_explain" says "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "run_explain" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "run_explain" says "run": a word for a change.
  What this check looks for
Description, as the server wrote it
Explain a run using its status, failed-case metadata, and evidence-lineage summary.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
runs_listList evaluation runs with stable cursors and regression signals.1 finding
Why it is in this group
- The name "runs_list" says "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "runs_list" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "runs_list" says "run": a word for a change.
  What this check looks for
Description, as the server wrote it
List evaluation runs with stable cursors and regression signals.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

Only reads 9Looks things up and changes nothing.Show 9 read-only tools

baseline_lineageShow the published baseline anchor and its evidence lineage.No findings
Why it is in this group
- The description's first verb is "show": a word for reading.
Description, as the server wrote it
Show the published baseline anchor and its evidence lineage.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
connections_catalogInspect all connector definitions and exact installed setup paths.No findings
Why it is in this group
- The description's first verb is "inspect": a word for reading.
Description, as the server wrote it
Inspect all connector definitions and exact installed setup paths. Unavailable blueprints and live verification are separate facts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
connections_graphRead canonical connection references and currently visible exact resource revisions.1 finding
Why it is in this group
- The description's first verb is "read": a word for reading.
Findings
- Info
  The input schema at properties.id.description mentions "credential".
  Matched text
  inputSchema.properties.id.description: "...returned by connections.backfill, not a credential ID."
  What this check looks for
Description, as the server wrote it
Read canonical connection references and currently visible exact resource revisions. No source access grant or execution.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
connections_listList current workspace connection metadata, with source restrictions, freshness and bounded continuation.No findings
Why it is in this group
- The name "connections_list" says "list": a word for reading.
Description, as the server wrote it
List current workspace connection metadata, with source restrictions, freshness and bounded continuation. Does not reveal secrets or grant source access.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
connector_healthShow the latest connector-readiness reports for the organization.No findings
Why it is in this group
- The description's first verb is "show": a word for reading.
Description, as the server wrote it
Show the latest connector-readiness reports for the organization.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
docs_searchSearch the published OpenAPI operation catalog for relevant help.Reads private dataNo findings
Why it is in this group
- The name "docs_search" says "search": a word for reading.
What it can reach
- private-dataThe name "docs_search" says "search" and "doc": it reads documents.
Description, as the server wrote it
Search the published OpenAPI operation catalog for relevant help.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
evaluations_listList evaluations with a stable cursor for the organization.No findings
Why it is in this group
- The name "evaluations_list" says "list": a word for reading.
Description, as the server wrote it
List evaluations with a stable cursor for the organization.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
project_inspectInspect the evaluations and project keys available in the authenticated organization.No findings
Why it is in this group
- The name "project_inspect" says "inspect": a word for reading.
Description, as the server wrote it
Inspect the evaluations and project keys available in the authenticated organization.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
project_planReturn a non-mutating next-step plan for connecting a repository, evaluation, or trace source.Reads private dataNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "repository": it reads repositories.
Description, as the server wrote it
Return a non-mutating next-step plan for connecting a repository, evaluation, or trace source.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.

Reads private data2: Reads files, mail, messages, databases, secrets, calendars or repositories.; docs_search
project_plan
Reads text others write0: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 5, 2026, 03:18 UTC, unchanged since Nov 5, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable: yes
HTTP status of an anonymous initialize: 200
tools/list served without credentials: yes
Tools that change things, listed without credentials: 3
Protocol version: 2025-06-18
WWW-Authenticate on 401: not observed
resource_metadata in WWW-Authenticate: not observed
RFC 9728 protected resource metadata: https://www.evalgate.com/.well-known/oauth-protected-resource/api/mcp
Authorization servers: https://www.evalgate.com
Legacy HTTP+SSE transport: no
Dynamic client registration: yes
Client ID metadata documents: no

WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
Matched text
https://www.evalgate.com/api/mcp: tools/list returned 12 tools to an anonymous client, including runs_list (write), run_explain (write), connections_roots (write)
What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 warn1 info

Warnruns_list
The server marks "runs_list" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "runs_list" says "run": a word for a change.
What this check looks for
Warnrun_explain
The server marks "run_explain" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "run_explain" says "run": a word for a change.
What this check looks for
Infoconnections_graph
The input schema at properties.id.description mentions "credential".
Matched text
inputSchema.properties.id.description: "...returned by connections.backfill, not a credential ID."
What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

All changes to this server

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

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

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__evalgate__project_inspect",
      "mcp__evalgate__project_plan",
      "mcp__evalgate__evaluations_list",
      "mcp__evalgate__baseline_lineage",
      "mcp__evalgate__docs_search",
      "mcp__evalgate__connector_health",
      "mcp__evalgate__connections_list",
      "mcp__evalgate__connections_catalog",
      "mcp__evalgate__connections_graph"
    ],
    "ask": [
      "mcp__evalgate__runs_list",
      "mcp__evalgate__run_explain",
      "mcp__evalgate__connections_roots"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as evalgate. Review it before you use it.

Capability tags behind 2 rules

mcp__evalgate__project_plan private-data
mcp__evalgate__docs_search private-data

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://anlyon.dev/api/v1/servers/com.evalgate/evalgate/verify?hash=f9c473fc8e39bda92ffdf3d676b41054f8e445257a0badaa27d96e3f67ca007b" | jq -e '.changed == false'

Pinned hash f9c473fc8e39, from Nov 5, 2026, 03:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/com.evalgate/evalgate/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

[![anlyon.dev](https://anlyon.dev/badge/com.evalgate/evalgate.svg)](https://anlyon.dev/servers/com.evalgate/evalgate)

Source: MCP Registry. Synced Nov 5, 2026, 03:17 UTC.