Browser automation · MCP server
Web search: MCP server, setup and security
Web search is an MCP server published on GitHub that lets an AI agent search the web using results from the Google search engine. Its repository has 472 stars and its last commit is from December 30, 2024, but it declares no licence.
What Web search does
According to its repository: “Web search using Google search results.”
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. Web search is listed under Browser automation, a category of 109 servers in the directory, where it ranks #30 by stars.
Installing and connecting Web search
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 Web search:
- 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.
- No licence: without a licence the code is not legally reusable, even if it is public. Avoid it in a company setting without the author's agreement.
- Maintenance: no commit for 22 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 December 30, 2024, the pskill9/web-search repository has 472 stars and 77 forks, with 6 open issues. It has more stars than 87% of the servers in the directory. Last change 22 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
Web search is still a modest project: read its code and compare it with the alternatives before using it.
Strengths
- Widely followed: 472 stars
Limitations
- No commit for 22 months
- No licence declared
- Install from source
Avoid if…
- You cannot isolate the agent (sandbox, container)
- Company use without the author's agreement
- 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 Web search?
No package is declared in the MCP registry: clone the pskill9/web-search repository, follow its README, then declare the start command in your client's MCP configuration.
Is Web search free?
The code is public but has no declared licence: it is not formally free to reuse.
Is Web search safe?
Points to watch: system access, no licence, and maintenance. Give it minimum rights and approve sensitive actions.
Is it an official server?
Nothing says so: it is a project published by pskill9 on GitHub. Check who maintains it before giving it access.
What are the alternatives to Web search?
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