agentgo-mcp
Related Servers
Alternatives to agentgo-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceMCP server that lets AI agents drive the locally installed Chrome or Edge, opening pages, taking compact accessibility-tree snapshots with @e references, and clicking, typing, scrolling, or capturing screenshots. It also exposes multi-account and cross-channel tab switching, tab sync rules, and ad-block/perf statistics.MIT
- AlicenseAqualityDmaintenanceAgent-native browser control MCP server that enables AI agents to browse and interact with web pages via accessibility tree snapshots and ref ID-based commands.152MIT
- AlicenseAqualityBmaintenanceMCP server that lets AI agents drive your real Chromium browser with your existing signed-in sessions, providing visible, local, and inspectable automation for tasks like navigation, clicking, typing, and form filling.251Apache 2.0
- FlicenseNot gradedqualityAmaintenanceA real Chromium browser for AI agents, driven over MCP: compact page outlines with stable refs, diff-only replies after each action, real mouse and keyboard input, the agent's own signed-in accounts, and human approval for payments. Windows 11.2-
- FlicenseNot gradedqualityCmaintenanceMCP server that wraps agent-browser to let LLMs control a real browser, providing tools for navigation, interaction, reading page content, accessibility snapshots, screenshots, and session management.1-
- FlicenseAqualityBmaintenanceAn MCP server that enables remote observation and control of a Chromium browser via a WebSocket relay, supporting DOM, CDP, and native OS automation for local or LAN-based AI agents.8-
TDQS
Scored across 11 tools
Most tools have clearly distinct purposes: reading, acting, waiting, navigation, screenshots, tabs, accounts, and human handoff are separable. Minor overlap exists between browser_act and browser_batch (batch runs multiple acts), between browser_open and browser_tabs op=new (both can open a URL), and browser_call acts as a wildcard that could duplicate any dedicated tool.
All tool names use a consistent browser_ prefix and snake_case, making the set easy to scan. The only minor inconsistency is that some names are verb-led (browser_read, browser_act) while others are noun-led (browser_tabs, browser_account), but the pattern remains predictable.
Eleven tools is well within the typical 3-15 range and each tool covers a meaningful part of browser automation. The set avoids redundancy while still offering specialized tools like batch, wait_human, and account handling.
The surface covers the full browser lifecycle: open/navigate, read, act, batch actions, wait, screenshot, tab management, accounts, and human handoff. browser_call provides a documented escape hatch for any protocol method not exposed as a dedicated tool, so there are no obvious dead ends.