A local testing tool for checking whether an AI agent can safely use your internal web application. It runs browser tasks with Playwright, a browser automation tool, and measures forbidden actions.

Use it to write YAML test suites for your own web app, run them locally, and add safety checks to automated deployments.

It helps find unsafe agent behavior before the agent reaches production. Its safety score can be used to block a CI/CD release, meaning an automated build or deployment.

deskcert — MCP server by RudrenduPaul/DeskCert-CLI

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/RudrenduPaul/DeskCert-CLI

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

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/mcp/rudrendupaul/deskcert-cli/deskcert/github.svg)](https://agentmods.dev/mcp/rudrendupaul/deskcert-cli/deskcert)

Your own site

<a href="https://agentmods.dev/mcp/rudrendupaul/deskcert-cli/deskcert"><img src="https://agentmods.dev/badge/mcp/rudrendupaul/deskcert-cli/deskcert/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/mcp/rudrendupaul/deskcert-cli/deskcert"><img src="https://agentmods.dev/badge/mcp/rudrendupaul/deskcert-cli/deskcert.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 Not applicable: nothing here is loaded into a session.

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

deskcert 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 1mo ago.

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.

python/server.json · 10 lines

What it actually says

{
  "deskcert": {
    "command": "uvx",
    "args": [
      "deskcert-cli",
      "deskcert-cli"
    ],
    "env": {}
  }
}

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.

1mo ago First seen · 10 lines scan A f4682176dfdb

Subscribe to this mod's changes

deskcert is an MCP server published in the GitHub repository RudrenduPaul/DeskCert-CLI (0 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-31.

Browser automation CI and CD DevOps and cloud Planning agent-evaluation agent-safety browser-automation computer-use mcp

uivision-mcp

MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input. Runs locally from the uivision-mcp-bridge npm package. Needs 1 environment variable to run.

A9T9/RPA · not measured

pixelcheck

Real eyes and hands on the web for AI agents. MCP-first. Local-first. Vendor-agnostic. Runs locally from the pixelcheck npm package. Needs 1 environment variable to run.

xcodethink/pixelcheck · not measured

mcp-vision-runtime

MCP server "mcp-vision-runtime" as configured in hussainn7/mcp-vision. Runs locally from the mcp-vision-runtime Python package.

hussainn7/mcp-vision · not measured

ecobrowser

AI-native browser framework — the AI's hands and eyes on the web. Structured (no-pixel) perception, verified self-healing actions, incremental diff perception, a live view — as a TypeScript library and an MCP server. Runs locally from the ecobrowser npm package.

HaidarESBER/ai-browser · not measured

hermes-computer-use

Pixel-level browser automation MCP server for WSL2 — drive a real Chrome with screenshot + xdotool, no CDP. Runs locally from the hermes-computer-use Python package.

Noah3521/hermes-computer-use · not measured

browser-use

Make websites accessible for AI agents. Runs locally from the browser-use Python package.

browser-use/browser-use · not measured