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.
git clone --depth 1 https://github.com/inggerman/mcpsWrote 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.
[](https://agentmods.dev/mcp/inggerman/mcps/mcp-browser)<a href="https://agentmods.dev/mcp/inggerman/mcps/mcp-browser"><img src="https://agentmods.dev/badge/mcp/inggerman/mcps/mcp-browser/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.
<a href="https://agentmods.dev/mcp/inggerman/mcps/mcp-browser"><img src="https://agentmods.dev/badge/mcp/inggerman/mcps/mcp-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mcp-browser 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What else claude_desktop_config.json configures
This page is one entry in a file that holds 58. Installing the file brings all of them; each is measured and scanned on its own page.
- MCP server mcp-agent-runner A not measured
- MCP server mcp-architecture A not measured
- MCP server mcp-argocd A not measured
- MCP server mcp-best-practices A not measured
- MCP server mcp-calendar A not measured
- MCP server mcp-ci-cd A not measured
- MCP server mcp-cluster-doctor C not measured
- MCP server mcp-code-quality A not measured
- MCP server mcp-config-sync A not measured
- MCP server mcp-database A not measured
- MCP server mcp-deploy-tracker C not measured
- MCP server mcp-design-patterns A not measured
- MCP server mcp-docker A not measured
- MCP server mcp-documentation A not measured
- MCP server mcp-documents A not measured
- MCP server mcp-event-driven A not measured
- MCP server mcp-fetch A not measured
- MCP server mcp-filesystem A not measured
- MCP server mcp-git A not measured
- MCP server mcp-gitea A not measured
- MCP server mcp-github A not measured
- MCP server mcp-gob-mexico A not measured
- MCP server mcp-harbor A not measured
- MCP server mcp-health-monitor A not measured
- MCP server mcp-image-builder A not measured
- MCP server mcp-java-build A not measured
- MCP server mcp-kafka A not measured
- MCP server mcp-kubernetes A not measured
- MCP server mcp-llm-router A not measured
- MCP server mcp-log-explorer A not measured
- MCP server mcp-markdown A not measured
- MCP server mcp-n8n A not measured
- MCP server mcp-network-doctor C not measured
- MCP server mcp-node-ops C not measured
- MCP server mcp-notify A not measured
- MCP server mcp-object-storage A not measured
- MCP server mcp-observability A not measured
- MCP server mcp-openapi A not measured
- MCP server mcp-orchestrator A not measured
- MCP server mcp-personal-vault A not measured
- MCP server mcp-postgres A not measured
- MCP server mcp-project-memory A not measured
- MCP server mcp-prompt-engineer A not measured
- MCP server mcp-rabbitmq A not measured
- MCP server mcp-redis A not measured
- MCP server mcp-security-champion A not measured
- MCP server mcp-smart-home A not measured
- MCP server mcp-snyk A not measured
- MCP server mcp-sonar A not measured
- MCP server mcp-source-validator A not measured
- MCP server mcp-storage-doctor C not measured
- MCP server mcp-structured-output A not measured
- MCP server mcp-tabular A not measured
- MCP server mcp-terraform A not measured
- MCP server mcp-vault-secrets A not measured
- MCP server mcp-vector-search A not measured
- MCP server mcp-web-search A not measured
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 · 19 lines scan A e1f99465f67b
mcp-browser is an MCP server published in the GitHub repository inggerman/mcps (0 stars, last pushed 28d ago), with no licence file. 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.
Other mcp servers, from other repositories
playwright
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
x-use
Browser-native AI agents for X (Twitter): multi-account, MCP-ready, no API keys required. Runs locally from the x-use-mcp Python package. Needs 2 environment variables to run.
chrome-devtools
Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the chrome-devtools-mcp npm package.
chrome-tabs
MCP server "chrome-tabs" as configured in pokutuna/mcp-chrome-tabs. Runs src/cli.ts with node.
fetch
Lets the agent fetch a URL and read its content as markdown. Runs locally from the mcp-server-fetch Python package.
chrome-devtools
Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the chrome-devtools-mcp npm package.