Skip to content

MCP Selection Lab

io.github.ChanghuLiu/mcp-selection-labChanghuLiustreamable-httpv0.5.2Scanned

Benchmark MCP tool selection with metadata-only routing, collision, abstention, and holdout checks.

3 tools: 1 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 1 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the MCP Selection Lab can do

The MCP Selection Lab is published by the GitHub account ChanghuLiu. It has 3 tools. It can create or change data (1 tool: scan_mcp_metadata), but cannot delete data. 2 tools only read.

1 tool brings in text other people can write (scan_mcp_metadata).

The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 15, 2026, version 0.5.2.

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.

3 tools

Changes things 1Claude Code: ask
  • scan_mcp_metadataCreate a free public report of MCP tool-description routing collisions.Reads text others write1 finding

    Why it is in this group

    • The description's first verb is "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...funds. Use a public HTTP(S) URL without credentials, query or fragment. Results use at..."

      What this check looks for
    Description, as the server wrote it
    Create a free public report of MCP tool-description routing collisions. Reads discovery metadata (initialize/tools/list) only; never calls target business tools or spends funds. Use a public HTTP(S) URL without credentials, query or fragment. Results use at most 12 tools and 24 generated cases, not a real-model evaluation. The returned report is enriched with agent_plan candidate description-only edits and a machine-readable rerun instruction. Candidate edits are not untouched-holdout proof. Reports persist and are public by link. For an existing report use get_selection_report. Set internal_test=true for owner/CI validation so it is excluded from public scans. source is a self-reported referral bucket, not identity verification.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: false
Only reads 2Show 2 read-only tools
  • get_selection_reportRead and agent-enrich an existing public scan report by id; no new target request or model call.No findings

    Why it is in this group

    • The name "get_selection_report" says "get": a word for reading.
    Description, as the server wrote it
    Read and agent-enrich an existing public scan report by id; no new target request or model call.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • selection_lab_infoGet free service capabilities, limits, privacy and connection details; does not scan a target.No findings

    Why it is in this group

    • The description's first verb is "get": a word for reading.
    Description, as the server wrote it
    Get free service capabilities, limits, privacy and connection details; does not scan a target.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true

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 private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
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 20, 2026, 18:57 UTC, unchanged since Oct 22, 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
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://agenttrustlab.com/mcp: tools/list returned 3 tools to an anonymous client, including scan_mcp_metadata (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 info

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.

Install

Pinned to version 0.5.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http selection-lab https://agenttrustlab.com/mcp
claude mcp add --transport http selection-lab https://agenttrustlab.com/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__selection-lab__selection_lab_info",
      "mcp__selection-lab__get_selection_report"
    ],
    "ask": [
      "mcp__selection-lab__scan_mcp_metadata"
    ],
    "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 selection-lab. Review it before you use it.

Capability tags behind 1 rule
  • mcp__selection-lab__scan_mcp_metadata untrusted-input

Pin

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://radar.anlyon.com/api/v1/servers/io.github.ChanghuLiu/mcp-selection-lab/verify?hash=4ca7e74707ac6d1bdd4501a2fe28304b92c9dc5f023f733ea50fde81ddd42b01" | jq -e '.changed == false'

Pinned hash 4ca7e74707ac, from Nov 15, 2026, 18:17 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.ChanghuLiu/mcp-selection-lab/changes.xml

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

Badge

Anlyon Radar badge for io.github.ChanghuLiu/mcp-selection-lab
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.ChanghuLiu/mcp-selection-lab.svg)](https://radar.anlyon.com/servers/io.github.ChanghuLiu/mcp-selection-lab)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:15 UTC.

MCP Selection Lab: questions and answers

Answered from the scan above, not from the publisher's description.

Is the MCP Selection Lab safe?

No scan can promise that. What its definitions show: 3 tools, 1 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the MCP Selection Lab delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the MCP Selection Lab do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the MCP Selection Lab have?

3 tools: 1 write, 2 read. scan_mcp_metadata, selection_lab_info and get_selection_report.

Does the MCP Selection Lab need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the MCP Selection Lab send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the MCP Selection Lab changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.