Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Browser Agent MCP Server

    1

    Let your agent drive real web pages via accessibility snapshots and stable element handles — fewer tokens and no fragile coordinate guessing.

    Free

    7 uses5.0 (1 review)
    Browser Agent MCP Server

    Browser Agent MCP Server

    Example session with this skill installed

    I'm building a support bot in Cursor that needs to log into our internal help desk and close resolved tickets. Screenshot-based attempts keep clicking the wrong buttons and burn tokens. Set up the accessibility-driven browser MCP server for me: register it in my mcp.json, then give me the exact navigate-snapshot-act loop my agent should follow. Context: standard React app with labeled inputs, the agent runs headless on Ubuntu behind an HTTP proxy, and we need to keep login state between sessions. Include the launch flags and any environment variables involved.

    • Read your context and instructions
    • Compiled the browser agent mcp

    Summary

    Your agent now drives the help desk through accessibility snapshots and handle-based clicks — no coordinate guessing. The server runs headless behind your proxy, persists login state in a dedicated profile, and registers as a single MCP entry in Cursor.

    {
      "mcpServers": {
        "web-agent": {
          "command": "npx",
          "args": ["@agent-infra/mcp-server-browser@latest", "--headless", "--proxy-server", "http://proxy.internal:3128", "--user-data-dir", "./.agent-profile", "--output-dir", "./.agent-out"]
        }
      }
    }
    
    StepToolRule
    1browser_navigateOpen the ticket URL once
    2browser_get_clickable_elementsOne snapshot per page state
    3click / fill / selectAct by handle index, never x/y
    4re-snapshotOnly after the page actually changed
    5screenshotFallback when labels are missing

    Next steps

    • Dry-run one resolved ticket before letting the bot close real ones
    • Add --vision only for canvas widgets; return to structured tools if a vision click misses
    • Keep .agent-profile out of git and inspect the download dir before sharing files

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Give your language model a real browser — without the pixel guessing. Instead of streaming screenshots to a vision model and hoping coordinates land, this reads pages through Puppeteer's accessibility tree and hands the model stable element handles. Clicks, form fills, scrolls and JS evaluation become repeatable at a fraction of the token cost. What you get: - Three connection modes: local stdio, a shared HTTP/SSE endpoint for workers, or in-process embedding for TypeScript runtimes - Full coverage: navigation, tabs, text and markdown extraction, interaction, screenshots, console JS, plus a vision fallback for canvas apps - Per-request headers for viewport, user agent and coordinate scaling — no restarts - A runbook for Docker displays, proxies, profile security and common failures Ship deterministic, cheaper, easier-to-debug browser agents.

    Canvas-based or label-poor pages fall back to slower vision clicks, which can miss when coordinate conventions differ; the HTTP/SSE endpoint ships unauthenticated, so public exposure requires your own reverse-proxy auth.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    5.0
    1 review
    5
    1
    4
    0
    3
    0
    2
    0
    1
    0

    This skill has been used 7 times.

    Trust & safety

    Security scan

    Security scan passed 2 months ago

    • Free with an Agensi account

    Requires

    Npmjs
    Node.js
    @agent-infra/mcp-server-browser
    It To An In Memory MCP

    Permissions

    Browser
    Environment Variables
    Write Files
    Network Access

    Allowed Hosts

    registry.npmjs.org

    File Scopes

    *.json
    *.ts

    Needs shell and network to install and launch the browser MCP server and drive real pages, plus write access for client config files and browser profiles.

    Listed2 months ago

    What's inside

    Frequently Asked Questions

    Unlike vision-only models that rely on imprecise X/Y coordinates, this skill uses Puppeteer’s accessibility tree to provide stable element handles. This significantly reduces token consumption, eliminates coordinate guessing, and makes interactions like form filling and clicking much more reliable.

    The server supports three distinct modes: local stdio for desktop use, an HTTP/SSE endpoint for distributed workers, and an in-process embedding option for TypeScript environments. This flexibility allows you to integrate browser capabilities into almost any infrastructure.

    Yes, while it prioritizes accessibility trees for efficiency, it includes full navigation, screenshot capabilities, and console JS evaluation. It even features a vision fallback to handle complex canvas-based applications where text-based selectors aren't available.

    This skill is built on the Model Context Protocol (MCP), making it compatible with any AI agent or platform that supports the MCP standard, such as Claude Desktop or custom TypeScript-based agent frameworks.

    You receive the full MCP server source code with multiple connection drivers, plus a comprehensive runbook. The runbook covers essential production topics like Docker display configuration, proxy setup, and managing profile security.

    New in LLM Ops