Skip to main content
Glama
Sign In
MCP Browser Extension

MCP Browser Extension

by Mehmoodqureshi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to MCP Browser Extension

No user-submitted related servers found.

    Related Servers

    • Chrome MCP Bridge

      randyrt
      F
      license
      Not graded
      quality
      D
      maintenance
      Enables 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
      -

    • cc-chrome

      joshoq
      A
      license
      B
      quality
      C
      maintenance
      Enables browser control through your existing signed-in Chrome profile, letting MCP clients like Claude Code manage tabs, navigate, inspect pages, and perform real user interactions via tool calls. Works with any model backend without needing Playwright or a fresh browser profile.
      21
      MIT

    • Controlium

      am-will
      A
      license
      Not graded
      quality
      D
      maintenance
      Chrome extension + MCP bridge that gives Claude control over your real browser via CDP, enabling navigation, clicking, typing, scrolling, screenshots, and JS execution with a visible cursor and tab-bring-to-front.
      1
      MIT

    • chrome-control-mcp

      masterdeepak15
      A
      license
      C
      quality
      B
      maintenance
      Enables MCP clients such as Claude to drive the user's real Chrome in the background via the DevTools Protocol through a companion extension, exposing 32 tools for navigation, form input, screenshots, snapshots, script evaluation, network and console inspection, performance tracing and raw CDP commands, with control off by default and limited by allowed sites and blocked domains.
      32
      25 npm
      1
      MIT

    • byob

      chenlememon371
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI coding tools to drive your real, already-logged-in Chrome browser through an extension-based local MCP bridge, with no debugging port or headless setup required. It provides tools for navigating pages, reading content, clicking, typing, screenshots, tabs, cookies, network inspection, and more.
      1 npm
      ISC
    Deploy Server
    Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

    TDQS

    B3.3/5.0

    Scored across 22 tools

    Disambiguation4/5

    Tools split into clear families (content reads, session/profile/task management, diagnostics) and descriptions sharply differentiate near-neighbours, e.g. get_html vs get_text vs read_as_markdown vs snapshot, and get_cookies vs storage. The main residual overlap is the several page-reading tools (get_text, read_as_markdown, extract_links, snapshot) which an agent may still hesitate between, plus three *_status tools that are close but scoped to different objects.

    Naming Consistency4/5

    Almost everything is snake_case with a verb or domain prefix (get_*, task_*, profile_*, *_status, *_list), which reads predictably. Minor deviations exist: tasks_list puts the plural noun first while sibling task_new/task_status are singular+verb, and several tools are bare nouns/actions (snapshot, screenshot, storage, batch, wait_for) rather than verb_noun.

    Tool Count4/5

    22 tools is on the heavy side of the 3-15 sweet spot, but the surface is genuinely broad (content extraction, frames, cookies/storage, profiles, tasks, proxy, batching) and each tool maps to a distinct capability rather than padding. Nothing feels redundant enough to drop.

    Completeness3/5

    The observation/diagnostic side is unusually thorough (HTML, text, markdown, links, snapshot, PDF, frames, auth walls, waits, page diffs, proxy, batching). However, the interaction side is largely absent: there is no navigate/click/type tool and no tab open/close despite descriptions referencing 'after a navigate' and 'open tabs', leaving a notable gap for actual browser automation workflows.

    Maintenance

    ActivityActive
    ResponsivenessResponsive

    Resources