agentic-browser
Related Servers
Alternatives to agentic-browser
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceEnables AI agents to control Chrome reliably over MCP, including multi-tab browsing, forms, clicks, keyboard, scrolling, drag, uploads, downloads, dialogs, JavaScript evaluation, and console/network inspection, in headed or headless mode or attached to an existing Chrome instance.22325 npmMIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to control and interact with a Chrome browser via MCP, providing tools for navigation, screenshots, clicking, form filling, content extraction, and tab management.1-
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to control the Google Chrome browser through a Node.js WebSocket bridge and a dedicated browser extension. It provides tools for capturing screenshots, executing JavaScript, managing tabs, and extracting page content via the MCP protocol.2-
- AlicenseBqualityFmaintenanceEnables AI agents to directly control your real Chrome browser with full context including login sessions, cookies, and open tabs. It provides tools for page scanning, JavaScript execution, CDP control, screenshots, and physical mouse/keyboard input for authentic browser automation.20245MIT
- AlicenseNot gradedqualityBmaintenanceEnables local Chrome control for AI clients over MCP stdio, HTTP, or CLI, exposing 20 tools to extract page text, number and click elements, type text, scroll, manage tabs, capture screenshots, and bind uploaded files to file inputs. Operations run entirely on the local machine with origin allowlists and refusal of untrusted URLs, without calling a cloud model or consuming model tokens.38 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to control Chrome browser actions like navigation, clicking, form filling, screenshots, and console/network logging via an MCP server and Chrome extension.605 npmMIT
TDQS
Scored across 35 tools
The core interaction tools (click, type, press, scroll, drag, select, upload) are cleanly separated, but the perception layer has four overlapping channels: browser_snapshot, browser_read, browser_extract and browser_screenshot all return page content, and browser_find vs browser_element_at vs browser_cursor all locate elements by different means. browser_wait and browser_watch both wait for page changes, and browser_cursor vs browser_cursor_style differ only subtly in name while doing unrelated things.
Every tool carries the same browser_ prefix and uses snake_case throughout, which makes the set highly predictable. The only inconsistency is grammatical: many names are verbs (navigate, click, extract, replay) while others are nouns (snapshot, tabs, events, history, stats, recipes, cursor), though each remains readable and guessable.
35 tools is well past the comfortable range for a single server and the surface sprawls into four sub-domains: core automation, perception, diagnostics (trace, stats, console, events), and a teaching/recording subsystem (teach_start, teach_stop, recipes, replay, record_start, record_stop). Several of these are convenience wrappers or observability extras that could be collapsed (batch, cursor_style, stats, trace) rather than separate tools.
The surface is unusually thorough: navigation, tabs, full input primitives, human handoff, downloads/dialogs, structured extraction, batch execution and a recipe-recording lifecycle are all covered with no obvious dead ends. Remaining gaps are real but niche for the domain: no iframe/frame targeting, no cookie or localStorage management, no viewport/device emulation, and no clipboard read beyond keyboard shortcuts.