Browser automation · MCP server
Ghostfox: MCP server, setup and security
Ghostfox is an open-source MCP server that lets an AI agent read pages using a stealth browser and record browsing evidence. Its repository has 11 stars and its last commit is from October 23, 2026 and it is licensed under MIT.
What Ghostfox does
According to its repository: “Self-hosted stealth browser built on a Firefox fork with fingerprint spoofing, shadow-DOM-aware page reading, login state detection and evidence recording.”
An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Ghostfox is listed under Browser automation, a category of 109 servers in the directory, where it ranks #89 by stars.
Topics declared by the repository: ai-agents, browser-automation, rust, stealth-browser, captcha-solver, firefox.
Installing and connecting Ghostfox
Distribution modes declared in the official MCP registry:
- PyPI package (Python, started with
uvxorpip) - npm package (Node.js, usually started with
npx)
Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Rust. Listed systems: macOS, Windows, Linux.
Security: what to check
An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.
Points found for Ghostfox:
- System access: the Browser automation category gives the agent control over files, a terminal, code or a browser. A booby-trapped instruction in content the agent reads (prompt injection) can then turn into an action.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on September 8, 2026, the autokeren/ghostfox repository has 11 stars and 3 forks, with 0 open issues. It has more stars than 28% of the servers in the directory. It received changes this month. Version published in the registry: 0.9.2 (October 6, 2026).
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
Ghostfox is a reasonable choice; check the points below before connecting it.
Strengths
- Active project: recent commit
- Listed in the official MCP registry
- Permissive licence (MIT)
Limitations
- Few visible users
Avoid if…
- You cannot isolate the agent (sandbox, container)
Alternatives
- Firecrawl MCP Server7.7K ★
- Browser use119K ★
- MCP server browser39.4K ★
- Playwright MCP38.6K ★
- SeleniumBase MCP13.1K ★
- Scrapling MCP Server89.4K ★
Learn more
Frequently asked questions
How do I install Ghostfox?
Ghostfox is distributed as PyPI package (Python, started with uvx or pip) and npm package (Node.js, usually started with npx). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of autokeren/ghostfox.
Is Ghostfox free?
The code is published under the MIT licence and can be used free of charge.
Is Ghostfox safe?
Points to watch: system access. Give it minimum rights and approve sensitive actions.
Is it an official server?
Nothing says so: it is a project published by autokeren on GitHub. Check who maintains it before giving it access.
What are the alternatives to Ghostfox?
In the same category: Firecrawl MCP Server, Browser use, MCP server browser, and Playwright MCP. Firecrawl MCP Server and Browser use score higher on our grid.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score