Skip to main content
Glama

Related Servers

Alternatives to sandboxed-browser-mcp

No user-submitted related servers found.

    Related Servers

    • A
      license
      B
      quality
      C
      maintenance
      Enables MCP clients to drive a real Chromium browser for automation, including navigation, JavaScript execution, CDP commands, network capture, and multi-tab control.
      7
      48 PyPI
      GPL 3.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents and clients to control a real Chromium browser through MCP tool calls, including navigation, clicking, typing, JavaScript evaluation, screenshots, and DOM snapshots. Supports multiple isolated sessions over authenticated HTTP with no disk writes.
      Apache 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables Codex or any MCP client to inspect and operate explicitly allowed browser tabs in paired Chromium profiles through a secure local-only bridge. Supports DOM snapshots with stable references, navigation, clicking, typing, scrolling, screenshots, and multiple sessions/profiles.
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to drive a Chromium browser through MCP, with persistent sessions, compact page snapshots, guarded actions, batched operations, and explicit result verification.
      16
      MIT
    • A
      license
      B
      quality
      C
      maintenance
      Enables an LLM to control a hosted headless Chromium browser over HTTP, navigating pages, clicking, typing, and reading structured accessibility snapshots so any MCP client can perform browser automation without local installation.
      23
      8,508,652 npm
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP clients to control Chrome/Edge browsers via CDP, including page navigation, element interaction, snapshots, network debugging, script execution, and performance tracing.
      AGPL 3.0

    TDQS

    A4.3/5.0

    Scored across 11 tools

    Disambiguation5/5

    Each tool targets a distinct action/input modality (navigate vs click vs type vs select vs key vs scroll), and the 'viewing' tools are explicitly differentiated: snapshot for structured viewport, get_text for full section text, find for locating off-screen elements, screenshot only for visual layout. Descriptions actively cross-reference each other to steer away from misselection.

    Naming Consistency4/5

    All tools use a consistent browser_ prefix in snake_case, with mostly verb-based names (navigate, click, type, scroll, find, get_text). Minor deviations like browser_back, browser_key, and browser_screenshot (noun-only) break the verb_noun pattern slightly but remain predictable.

    Tool Count5/5

    11 tools is well within the ideal 3-15 range, and each tool corresponds to a distinct browser interaction primitive without redundancy. The set feels deliberately scoped rather than padded.

    Completeness4/5

    Core browsing lifecycle is well covered: navigation, back, interaction (click/type/select/key), reading (snapshot/get_text/find/screenshot), and scrolling. Notable gaps remain: no hover (needed for many menus), no tab management despite 'current tab' framing, and no explicit wait-for-load/idle primitive.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues