A
licenseA
qualityD
maintenanceStealth browser automation for AI agents, using source-patched Chromium to bypass bot detection systems like Cloudflare, reCAPTCHA, and FingerprintJS.
28
Apache 2.0
real-browser-mcp-server
by codeiva11
Related Servers
Alternatives to real-browser-mcp-server
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to control browsers with human-like behavior, stealth anti-detection, and 70 tools for navigation, interaction, and monitoring.8 npm1MIT
- AlicenseAqualityCmaintenanceEnables AI agents to fully control a browser for web automation, including navigation, clicking, typing, scrolling, screenshots, and DOM inspection, with session persistence and anti-bot bypass.4027 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to perform stealth browser automation and anti-detection web interaction, including session management, humanized interactions, and bypassing anti-bot/WAF protections.MIT
- AlicenseNot gradedqualityCmaintenanceProvides undetectable browser automation for AI agents, bypassing Cloudflare and other anti-bot systems. Includes 97 tools for navigation, scraping, network interception, and element cloning.MIT
- AlicenseNot gradedqualityDmaintenanceUndetectable browser automation for AI agents that bypasses Cloudflare, antibot systems, and social media blocks using real browser instances with 97 tools across 11 sections.MIT
TDQS
B3.2/5.0
Scored across 21 tools
Disambiguation3/5
Most tools target distinct browser operations, but there is meaningful overlap: get_content, extract_data, and see_page all return page-derived information, and deep_analysis also inspects the page. Network-related tools like redirect_tracer, network_recorder, and replay_request have adjacent responsibilities, so agents may need careful reading to pick the right one.
Naming Consistency3/5
Names are consistently snake_case and readable, but the set mixes bare imperative verbs like navigate, wait, click, and type with compound noun-style names like storage_inspector, media_extractor, redirect_tracer, and api_analyzer. There is also inconsistency between similar extraction tools: get_content, extract_data, and see_page do not follow a single clear naming pattern.
Tool Count3/5
21 tools is at the heavy end for a browser automation server, even though browser workflows do require many distinct primitives. Some tools like random_scroll, progress_tracker, and api_analyzer feel peripheral and inflate the count beyond the core browsing capability set.
Completeness4/5
The tool surface covers the full browser automation lifecycle well: init, navigate, wait, interact, extract, inspect, network control, storage management, media handling, and close. Minor gaps such as explicit back/forward navigation, file upload, or a dedicated screenshot-only action exist, but agents can generally work around them with the provided generic tools.
Maintenance
ActivityActive
ResponsivenessNo issues