A management tool for reviewing and coordinating AI agents used by a company. It covers labelled metrics, work agreements, vendor bill checks, and a weekly decision queue.

Use it to review an AI-agent workforce, check job contracts and vendor bills, and organize weekly decisions about the agents.

It brings agent performance, responsibilities, costs, and pending management decisions into one review process.

metrx-desk — Plugin for Claude Code by metrxbots/mcp-server

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/metrxbots/mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/metrxbots/mcp-server/metrx-desk-plugin/github.svg)](https://agentmods.dev/plugins/metrxbots/mcp-server/metrx-desk-plugin)

Your own site

<a href="https://agentmods.dev/plugins/metrxbots/mcp-server/metrx-desk-plugin"><img src="https://agentmods.dev/badge/plugins/metrxbots/mcp-server/metrx-desk-plugin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/metrxbots/mcp-server/metrx-desk-plugin"><img src="https://agentmods.dev/badge/plugins/metrxbots/mcp-server/metrx-desk-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 5 skills, 1 MCP server cost 299 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

metrx-desk scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/metrx-desk-plugin/.claude-plugin/plugin.json · 16 lines

What it actually says

{
  "name": "metrx-desk",
  "version": "0.1.0",
  "description": "Manage the AI agents your company employs as a line manager would: a workforce review with labelled numbers, job contracts, a vendor bill check, and the weekly decision queue. The sample review needs no account.",
  "author": {
    "name": "Metrx",
    "url": "https://metrxbot.com"
  },
  "homepage": "https://docs.metrxbot.com/desk",
  "repository": "https://github.com/metrxbots/mcp-server",
  "license": "MIT",
  "keywords": ["ai-agents", "workforce", "cost", "job-contract", "mcp", "metrx"],
  "skills": "./skills",
  "mcpServers": "./.mcp.json"
}

Contents

What it installs

The manifest is a name and a version. 5 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 299 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 16 lines scan A ab5879782f7c

Subscribe to this mod's changes

metrx-desk is a plugin published in the GitHub repository metrxbots/mcp-server (2 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-10.

Analytics and metrics Building agents Cost Optimization LLM ai-agent finops mcp mcp-server

metrx-desk next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
metrx-deskmetrxbots/mcp-server	Plugin	2	2d ago	MIT	A	—	Claude Code
hyper-mcphyper-mcp-rs/hyper-mcp	Plugin	881	2d ago	Apache-2.0	A	—	Claude Code
livetennisapilivetennisapi/livetennisapi-mcp	Plugin	134	2d ago	MIT	A	—	Claude Code
mcp-zap-connectdtkmn/mcp-zap-server	Plugin	70	yesterday	Apache-2.0	A	—	Claude Code
umtMarkgatcha/universal-mcp-toolkit	Plugin	16	4d ago	MIT	A	—	Claude Code
declaudetenkenco/declaude	Plugin	1	2d ago	MIT	A	—	Claude Code
huggingfaceKlavis-AI/klavis	Plugin	5.8k	6d ago	Apache-2.0	A	—	Gemini CLI