agentmods.dev

arthur-runtime

arthur-runtime is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from sh7vansh/arthur. Its token cost is not measured, scanned A, original, MIT.

A local headless Chromium runtime for Gloria and AI agents. Headless Chromium is the Chrome browser running without a visible window.

In plain words
What is it for?
It is for browser-based work performed by Gloria and AI agents, though the specific operations are not described.
Why use it?
It provides browser runtime support for agents that need to run Gloria-related tasks.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

not rated 0 11d ago A scan tokens not measured original MIT
View the source file sh7vansh/arthur
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.

agentmods
npx agentmods add mcp/sh7vansh/arthur/arthur-runtime
Clone the repo
git clone --depth 1 https://github.com/sh7vansh/arthur

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.

agentmods badge for arthur-runtime

README.md
[![agentmods](https://agentmods.dev/badge/mcp/sh7vansh/arthur/arthur-runtime.svg)](https://agentmods.dev/mcp/sh7vansh/arthur/arthur-runtime)
Your own site
<a href="https://agentmods.dev/mcp/sh7vansh/arthur/arthur-runtime"><img src="https://agentmods.dev/badge/mcp/sh7vansh/arthur/arthur-runtime.svg" alt="Measured on agentmods" 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. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

arthur-runtime 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 4d 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.

listed in the official MCP registry · 8 lines

What it actually says

{ "arthur-runtime": { "command": "uvx", "args": [ "arthur-runtime" ] } }

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.

  1. 4d ago First seen · 8 lines scan A 6a825dcb29dc

Subscribe to this mod's changes

arthur-runtime is an MCP server published in the GitHub repository sh7vansh/arthur (0 stars, last pushed 11d ago), licensed MIT. 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 automationai-agentscdpchromiumdockerheadless-chromemcp
Related

Other mcp servers, from other repositories

mcp

Lightweight browser automation for AI agents: navigate, screenshot, extract, PDF. One small binary. Runs locally from the @kitewright/mcp npm package.

kitewright/kitewright · not measured

chrome-orchestrator

Python SDK and CLI for orchestrating Arthur and Gloria headless Chrome containers. Runs locally from the chrome-orchestrator Python package.

sh7vansh/chrome-orchestrator · not measured

cloakbrowser-mcp

Playwright MCP-compatible browser automation bridge for CloakBrowser Chromium. Runs locally from the cloakbrowser-mcp npm package. Needs 10 environment variables to run.

swimmwatch/cloakbrowser-mcp · not measured

maps-browser-mcp

MCP server "maps-browser-mcp" as configured in git-ksk/maps-browser-mcp. Runs locally from the maps-browser-mcp npm package.

git-ksk/maps-browser-mcp · not measured

wavexis-mcp

MCP server exposing the wavexis browser automation library to LLMs — 220 tools, 13 capability tiers, zero Node.js. Runs locally from the wavexis-mcp Python package.

MathiasPaulenko/wavexis-mcp · not measured

opencode-browser-mcp

Session-isolated browser automation over MCP and Chrome DevTools Protocol. Runs locally from the @mirsella/opencode-browser-mcp npm package.

mirsella/opencode-browser-mcp · not measured