Browser automation · MCP server
BrowserMCP: MCP server, setup and security
BrowserMCP is an open-source MCP server published on GitHub that lets an AI agent automate actions performed in your locally running Chrome browser. Its repository has 7,217 stars and its last commit is from April 24, 2025 and it is licensed under Apache-2.0.
What BrowserMCP does
According to its repository: “Automate your local Chrome browser.”
The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. BrowserMCP is listed under Browser automation, a category of 109 servers in the directory, where it ranks #11 by stars.
Topics declared by the repository: browser-automation, browser-extension, claude, cursor.
Installing and connecting BrowserMCP
No package or remote server is declared in the official MCP registry: you install it from source, following the repository README.
It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: TypeScript.
Security: what to check
Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.
Points found for BrowserMCP:
- 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.
- Maintenance: no commit for 18 months. Possible flaws and protocol changes are no longer tracked.
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 March 28, 2025, the BrowserMCP/mcp repository has 7,217 stars and 593 forks, with 135 open issues. It has more stars than 98% of the servers in the directory. Last change 18 months ago.
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
BrowserMCP is a reasonable choice; check the points below before connecting it.
Strengths
- Widely followed: 7.2K stars
- Permissive licence (Apache-2.0)
Limitations
- No commit for 18 months
- Install from source
Avoid if…
- You cannot isolate the agent (sandbox, container)
- Production use without reviewing the code
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 BrowserMCP?
No package is declared in the MCP registry: clone the BrowserMCP/mcp repository, follow its README, then declare the start command in your client's MCP configuration.
Is BrowserMCP free?
The code is published under the Apache-2.0 licence and can be used free of charge.
Is BrowserMCP safe?
Points to watch: system access and maintenance. Give it minimum rights and approve sensitive actions.
Is it an official server?
Nothing says so: it is a project published by BrowserMCP on GitHub. Check who maintains it before giving it access.
What are the alternatives to BrowserMCP?
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