softglaze-browser-mcp
Related Servers
Alternatives to softglaze-browser-mcp
- AlicenseBqualityCmaintenanceBridge to the MCP server built into SoftGlaze Browser, a multi-profile browser for Windows: AI apps can list, check and start isolated browser profiles (each with its own proxy and fingerprint), run macros and act inside pages. Changes wait for approval in the app; requires the SoftGlaze Browser desktop app.439MIT
Related Servers
- AlicenseNot gradedqualityDmaintenanceExposes authorized ChatGPT, DeepSeek, Kimi, and Grok web sessions to agents as MCP tools, including chat and local file attachments over HTTP or stdio.7MIT
- AlicenseNot gradedqualityCmaintenanceEnables browser-based AI chat interfaces to use local MCP tools by injecting a tool-call protocol into the page and executing approved filesystem, shell, and downstream MCP tool calls from a local daemon.598 npmAGPL 3.0

GenieOS MCP Serverofficial
AlicenseAqualityDmaintenanceStdio bridge for editors to connect to the GenieOS MCP server, enabling AI agents to interact with GenieOS via Streamable HTTP transport.6413 npmMIT- AlicenseNot gradedqualityBmaintenanceEnables AI clients to connect to remote OAuth 2.0-protected MCP servers through a zero-config stdio-to-Streamable HTTP bridge with automatic discovery, PKCE login, and silent token refresh.393 npm1MIT
- AlicenseNot gradedqualityDmaintenanceBridges stdio-based LLM harnesses to OAuth-protected remote MCP servers via Streamable HTTP, handling PKCE browser login and token refresh automatically.8 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables web-based AI chat clients to securely operate a local computer through an OAuth-gated MCP endpoint, exposing governed tools for files, shell, search, Git, SQLite, browser automation, DevTools, background tasks, localhost services, clipboard, notifications, ports, Postman, and AIObox windows.MIT
TDQS
Scored across 39 tools
Most tools target a distinct resource+action, and descriptions explicitly separate near-neighbors (get_proxy_health vs check_proxy, page_snapshot vs page_extract_text, stop_run vs stop_profile). A few boundaries are still soft: profile_health vs get_proxy_health overlap on proxy diagnostics, and start_profile vs run_macro vs start_warmer all start browsing activity, though each is explained. Overall an agent can pick correctly with modest care.
Dominated by snake_case verb_noun (list_profiles, create_group, move_profiles_to_group, check_proxy), with a clean page_* prefix family for browser actions. Minor deviations: noun-only names like workspace_summary and profile_health sit beside get_proxy_health, and batch_generate_profiles vs create_profile use different verbs for creation. Still highly predictable.
39 tools is heavy, but the server spans several genuinely separate sub-domains (profiles, proxies, groups, macros, runs, page automation, memory, activity/sessions), each with a small coherent set. There is consolidation room — nine page_* tools and three stop_* variants could be trimmed — so it sits at the borderline rather than being well-scoped.
Coverage is broad and lifecycle-aware for reading and running (profiles, proxies, macros, runs, page interaction, memory, sessions), which is impressive. However, the surface is create/update-heavy with no delete or rename for profiles, groups or macros, and no cookie/2FA or export/import operations, leaving real gaps for housekeeping workflows.