MCP Selection Lab

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

Connector by ChanghuLiu · GitHub account verified by the MCP Registry

IndexedLicense unknownRemote (HTTP)

Chalk Labs

Need help deploying MCP Selection Lab?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/changhuliu-mcp-selection-lab

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

https://agenttrustlab.com/mcp Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

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

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools: 2 read · 1 write · 0 delete
Secrets: None asked for
Install scripts: Nothing to install (hosted)
Runs as: Hosted (remote endpoint)

Tools by what they do 3

From the running server's own tool list (tools/list) on Oct 25, 2026.

Read 2 · Look things up without changing anything.

get_selection_report
selection_lab_info

Write 1 · Create, change, send or run things.

scan_mcp_metadata

Network hosts it talks to 1

agenttrustlab.com · found in remote endpoint, install command

Files it touches

Any path the agent passes to its tools

Tools (3)

As the server listed them on Oct 25, 2026. Descriptions are the server’s own words; hidden characters are shown as [U+…].

get_selection_reportread-only
Read and agent-enrich an existing public scan report by id; no new target request or model call.
scan_mcp_metadata
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_selecti…
selection_lab_inforead-only
Get free service capabilities, limits, privacy and connection details; does not scan a target.

Signals

Last release: Oct 13, 2026 (29 days ago)
Repository: Not found on GitHub (deleted or private)

Details

Registry name: io.github.ChanghuLiu/mcp-selection-lab
Version: 0.5.2
Auth: Auth not stated
License: License unknown
Repository: github.com/ChanghuLiu/mcp-selection-lab
Website: agenttrustlab.com/
First seen: Oct 24, 2026
Last checked: Nov 1, 2026
Source: Official MCP Registry

Rank

of 45,943 in Connectors

Score

0.573

How ranking works →

Grades

Freshness

Active in the last 30 days. Last activity 29 days ago.

–

Security

Security scan: in progress. Grades from our dependency, secret, code and prompt-injection checks appear here once they launch. Until then, check the code before you install.

Indexed

Found automatically from a public source. Not yet claimed by its publisher.

How grades work →

Availability

100% uptime, last 30 days (1 check)

Last check: 17 days ago
Status: Up
Median response: 351 ms

Up
Up, auth required
Down
Not checked
No data

A daily MCP handshake with the remote endpoint. “Auth required” means it answered and wants a login or key. “Not checked” means the URL needs your own account or blocks automated checks.

Is this yours?

Claim it to add pricing, screenshots and docs, and to get a verified badge.

Claim listing Suggest a fix

Report a security problem

More from ChanghuLiu

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped: 50+; launches shipped
media placements: 500+; media placements
founders on every account: 2; founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get MCP Selection Lab running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Need help deploying MCP Selection Lab?

Call Get help

Cite this page

MCP Selection Lab. Agent Mart. https://agentmart.dev/connectors/changhuliu-mcp-selection-lab (last updated 2026-11-01)