chrome-agent-bridge
Related Servers
Alternatives to chrome-agent-bridge
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables MCP-compatible agents and HTTP clients to discover, claim, and control Chrome tabs through an authenticated local bridge, including snapshots, actions, approvals, task ownership, screenshots, frames, diagnostics, and cleanup.Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables MCP-compatible agents to securely control the user's already authenticated Chrome browser via explicit tab authorization and DOM-based actions.1Apache 2.0
- AlicenseNot gradedqualityAmaintenanceMCP 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
- AlicenseNot gradedqualityDmaintenanceLocal MCP server for persistent Chrome automation with multi-profile support, enabling tab management, page inspection, element interaction, JavaScript evaluation, and screenshots while preserving login sessions across restarts.227 npm3MIT
- AlicenseAqualityAmaintenanceMCP server that drives your real Chrome/Edge/Opera browser through a Chrome extension and DevTools Protocol, preserving logins and session state, and can also perform OS-level mouse and keyboard input behind approval.512MIT
- AlicenseNot gradedqualityAmaintenanceMCP server for browser automation, exposing tools for tab management, navigation, CDP, action plans, and cleanup.1,325 npm405MIT
TDQS
Scored across 101 tools
Several clusters contain near-duplicate or heavily overlapping tools, notably the JS analysis/deobfuscation set (js_deobfuscate_pipeline, analysis_decode_string_array, analysis_deflat_control_flow, js_solve_constraints, ast_transform_apply) and the proto_* inference family. The compatibility browser_click/browser_fill versus browser_act trio is explicitly redundant, and debugger_get_paused_state/debugger_wait_for_paused/debugger_capture_hit require careful reading to distinguish. Many tools are distinct, but the amount of overlap forces agents to read fine print to choose.
The server mostly uses snake_case, but prefixes are inconsistent across subsystems (browser_, debugger_, network_, proto_, sourcemap_, analysis_, ast_, js_, binary_, wasm_) and several tools carry no prefix at all (watch, breakpoint, collect_code, understand_code, detect_crypto). Verb ordering also varies (noun_verb vs verb_noun). It is readable but not a single predictable convention.
101 tools is an extreme over-scoping for a single server, blending browser automation, dedicated CDP debugging, network forensics, protobuf/gRPC parsing, WASM inspection, source-map tooling, and static JS analysis. Even if every tool earns some niche, the set is far past the point where an agent can hold the surface in mind.
Each sub-domain (tabs, debugger, network, sourcemaps, proto/WASM analysis) has reasonable if partial coverage, but the sheer breadth means no single domain is fully round-tripped. Core browser actions and debugger control are fairly complete, yet the sprawl suggests many areas have notable gaps that would surface in real workflows.