In-depth architectural comparison of the Cdpilot and Rrweb Stack MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Cdpilot
Browser Automation · Local stdio
Quality: 40/100 (Fair) | Auth: No auth required
Rrweb Stack
Browser Automation · Local stdio
Quality: 52/100 (Good) | Auth: No auth required
Verdict Summary: Choose Cdpilot if you need specialized Browser Automation tools running via a local process. Choose Rrweb Stack if your workspace requires Browser Automation integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Cdpilot when:
You need dedicated capabilities in the Browser Automation domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Primary tools included: Raw CDP browser automation, MCP interface for AI clients, Isolated per-project browser profiles.
Zero-dependency browser automation over raw CDP — no Puppeteer, Playwright, or Selenium.
Local-first MCP server (@peekdev/mcp) + Chrome extension that records your real authenticated browser session (rrweb DOM + console + network, PII-masked, to local SQLite) and lets AI coding agents query it or drive the browser. No cloud, no telemetry.
Cdpilot is categorized under Browser Automation and uses a local stdio subprocess. In contrast, Rrweb Stack belongs to Browser Automation using local stdio subprocess. Select Cdpilot when you need capabilities focused on browser automation and Rrweb Stack when you require tools for browser automation.