mare-browser-mcp
Related Servers
Alternatives to mare-browser-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceLocal browser automation MCP server for Claude Code, enabling navigation, clicking, typing, and inspecting real web pages via Google Chrome.18 npm1MIT
- FlicenseNot gradedqualityBmaintenanceA Chrome browser automation MCP server. Connect Claude (or any MCP client) to a real Chrome session — using your existing profiles with their cookies, saved passwords, and history.3-
- AlicenseNot gradedqualityAmaintenanceMCP server to control a real Chrome browser from Claude, enabling navigation, DOM snapshots, clicks, typing, screenshots, and JS execution via a Chrome extension bridge.MIT
- AlicenseAqualityDmaintenanceSelf-hosted MCP server for AI browser automation. Connects to your own Chromium instance via CDP, providing tools for browser control, navigation, interaction, and content extraction.191MIT
- AlicenseCqualityDmaintenanceAn MCP server that gives Claude Code real browser control for web automation, testing, and screenshots.3223 npm151MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP Server for Chrome DevTools, following the Chrome DevTools Protocol. Integrates with Claude Desktop and Claude Code.308MIT
TDQS
Scored across 14 tools
Each tool has a clearly distinct purpose: navigation, action execution, debugging, DOM querying, snapshotting, waiting, screenshotting, JS eval, scrolling, restarting, uploading, network waiting, and device emulation. Even the inspection tools (debug, query, snapshot, eval) are well separated by what they return and when to use them.
All 14 tools follow the consistent pattern of 'browser_' prefix followed by a lowercase verb (navigate, act, debug, query, fetch, snapshot, wait_for_url, screenshot, eval, scroll, restart, upload, wait_for_network, emulate_device). No mixing of camelCase or inconsistent verb styles.
14 tools is within the ideal 3-15 range and each tool serves a distinct aspect of browser automation—navigation, interaction, inspection, waiting, debugging, device emulation, and file upload. The count is well-scoped for a comprehensive browser control server without being bloated.
The server covers the full lifecycle of browser interaction: navigate, act, inspect, wait, debug, screenshot, and emulate. Minor gaps exist such as no explicit dialog acceptance (alert/confirm/prompt) or tab management, but agents can work around these with browser_eval in most cases, so they are not critical dead ends.