Browser automation · MCP server
Peek: MCP server, setup and security
Peek is an open-source MCP server published on GitHub that lets an AI agent record authenticated browser sessions locally and query events or drive browsing. Its repository has 8 stars and its last commit is from July 10, 2026 and it is licensed under Apache-2.0.
What Peek does
According to its repository: “Record your authenticated browser session (rrweb DOM, console, network) to local SQLite with PII masking, so coding agents can query it or drive the 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. Peek is listed under Browser automation, a category of 109 servers in the directory, where it ranks #95 by stars.
Topics declared by the repository: ai-coding-agent, apache-2, chrome-extension, claude-code, cursor, cypress.
Installing and connecting Peek
Distribution modes declared in the official MCP registry:
- npm package (Node.js, usually started with
npx)
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 Peek:
- 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 May 26, 2026, the Cubenest/rrweb-stack repository has 8 stars and 0 forks, with 1 open issues. It has more stars than 22% of the servers in the directory. Last change 4 months ago. Version published in the registry: 0.1.0-alpha.24 (July 9, 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
Peek is still a modest project: read its code and compare it with the alternatives before using it.
Strengths
- Listed in the official MCP registry
- Permissive licence (Apache-2.0)
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 Peek?
Peek 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 Cubenest/rrweb-stack.
Is Peek free?
The code is published under the Apache-2.0 licence and can be used free of charge.
Is Peek 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 Cubenest on GitHub. Check who maintains it before giving it access.
What are the alternatives to Peek?
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