Browser automation · MCP server
Safari MCP: MCP server, setup and security
Safari MCP is an open-source MCP server that lets an AI agent automate the Safari browser natively without a Chrome dependency. Its repository has 224 stars and its last commit is from October 23, 2026 and it is licensed under MIT.
| Adoption (stars) | 24/40 | |
|---|---|---|
| Maintenance | 30/30 | |
| Framework (licence, registry, official) | 20/30 |
What Safari MCP does
According to its repository: “Native Safari browser automation without a Chrome dependency.”
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. Safari MCP is listed under Browser automation, a category of 109 servers in the directory, where it ranks #40 by stars.
Topics declared by the repository: applescript, browser-automation, claude, cursor, macos, safari.
Installing and connecting Safari MCP
Distribution modes declared in the official MCP registry:
- 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: TypeScript. Listed systems: macOS.
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 Safari MCP:
- 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 March 18, 2026, the achiya-automation/safari-mcp repository has 224 stars and 33 forks, with 10 open issues. It has more stars than 79% of the servers in the directory. It received changes this month. Version published in the registry: 2.22.18 (October 19, 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
Safari MCP is a reasonable choice; check the points below before connecting it.
Strengths
- Active project: recent commit
- Widely followed: 224 stars
- Listed in the official MCP registry
- Permissive licence (MIT)
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 Safari MCP?
Safari MCP is distributed as 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 achiya-automation/safari-mcp.
Is Safari MCP free?
The code is published under the MIT licence and can be used free of charge.
Is Safari MCP 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 achiya-automation on GitHub. Check who maintains it before giving it access.
What are the alternatives to Safari MCP?
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