# MCP Selection Lab (remote · agenttrustlab.com)

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

- Trust score: 82/100 (high trust)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `agenttrustlab.com`: 82/100 (this document), [markdown](https://verifymcp.io/servers/changhuliu-mcp-selection-lab/agenttrustlab.md), [page](https://verifymcp.io/servers/changhuliu-mcp-selection-lab/agenttrustlab)

## Channel facts

- Endpoint: `https://agenttrustlab.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.5.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 374 tokens (~124/item across 3 items; 3 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the MCP Selection Lab server?

MCP Selection Lab is a hosted endpoint at https://agenttrustlab.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http changhuliu-mcp-selection-lab 'https://agenttrustlab.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "changhuliu-mcp-selection-lab": {
      "url": "https://agenttrustlab.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "changhuliu-mcp-selection-lab": {
      "type": "http",
      "url": "https://agenttrustlab.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.changhuliu-mcp-selection-lab]
url = "https://agenttrustlab.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "changhuliu-mcp-selection-lab": {
      "type": "remote",
      "url": "https://agenttrustlab.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add changhuliu-mcp-selection-lab --url 'https://agenttrustlab.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  changhuliu-mcp-selection-lab:
    url: "https://agenttrustlab.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "changhuliu-mcp-selection-lab": {
      "Transport": "http",
      "Url": "https://agenttrustlab.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add changhuliu-mcp-selection-lab -t streamable-http -u 'https://agenttrustlab.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "changhuliu-mcp-selection-lab": {
      "type": "http",
      "url": "https://agenttrustlab.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-12 (score 82, 0)

- [security] Stability: 0.97 → pass

### 2026-11-11 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-08 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-07 (score 80, 0)

- [functional improvement] Endpoint reachability: unreachable → reachable

### 2026-11-06 (score 80, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-11-05 (score 79, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] HSTS header: fail → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] TLS certificate: pass → unverified
- [security regression] Stability: 0.73 → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-11-04 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (3)

### `selection_lab_info` (~27 tokens)

Get free service capabilities, limits, privacy and connection details; does not scan a target.

### `scan_mcp_metadata` (~186 tokens)

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.

Input parameters:

- `internal_test` (boolean)
- `mcp_url` (string, required)
- `source` (string)

### `get_selection_report` (~38 tokens)

Read and agent-enrich an existing public scan report by id; no new target request or model call.

Input parameters:

- `report_id` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/changhuliu-mcp-selection-lab/agenttrustlab#diagnostics

## Score history

- 2026-11-21: 82
- 2026-11-20: 82
- 2026-11-19: 82
- 2026-11-18: 82
- 2026-11-17: 82
- 2026-11-16: 82
- 2026-11-15: 82
- 2026-11-14: 82
- 2026-11-13: 82
- 2026-11-12: 82
- 2026-11-11: 82
- 2026-11-10: 81
- 2026-11-09: 81
- 2026-11-08: 81
- 2026-11-07: 80
- 2026-11-06: 80
- 2026-11-05: 79
- 2026-11-04: 79
- 2026-11-03: 78
- 2026-11-02: 78
- 2026-11-01: 77
- 2026-10-31: 77
- 2026-10-30: 76
- 2026-10-29: 76
- 2026-10-28: 75
- 2026-10-27: 75
- 2026-10-26: 74
- 2026-10-25: 74
- 2026-10-24: 74
- 2026-10-23: 73

## Common questions

### What is the MCP Selection Lab server?

MCP Selection Lab is listed in the public MCP registry as io.github.ChanghuLiu/mcp-selection-lab. Benchmark MCP tool selection with metadata-only routing, collision, abstention, and holdout checks. This page covers its hosted endpoint (https://agenttrustlab.com/mcp).

### Is the MCP Selection Lab server safe to use?

MCP Selection Lab scores 82 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the MCP Selection Lab server expose?

MCP Selection Lab exposes 3 tools: selection_lab_info, scan_mcp_metadata, get_selection_report. Their descriptions and schemas cost roughly 251 tokens of context every time the server is loaded.

### Does the MCP Selection Lab server require authentication?

No. We connected to MCP Selection Lab without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the MCP Selection Lab server still maintained?

MCP Selection Lab is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the MCP Selection Lab server?

VerifyMCP ran 13 checks on MCP Selection Lab, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://agenttrustlab.com/mcp
- Repository: https://github.com/ChanghuLiu/mcp-selection-lab
- Website: https://agenttrustlab.com/
- Changelog RSS feed: https://verifymcp.io/servers/changhuliu-mcp-selection-lab/agenttrustlab.xml
- Changelog JSON feed: https://verifymcp.io/servers/changhuliu-mcp-selection-lab/agenttrustlab/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/changhuliu-mcp-selection-lab/agenttrustlab.json
- HTML version of this page: https://verifymcp.io/servers/changhuliu-mcp-selection-lab/agenttrustlab
