/ Verzeichnis / Playground / Browser Tools
● Community AgentDeskAI ⚡ Sofort

Browser Tools

von AgentDeskAI · AgentDeskAI/browser-tools-mcp

Read live console logs, network errors, DOM, and screenshots from YOUR real Chrome — debugging context straight into your agent.

AgentDeskAI's browser-tools MCP ships a Chrome extension + local bridge + MCP server. Your agent sees what YOU see — logged-in sessions, extensions, the real DOM and console. Best for debugging sessions where reproducing in a clean browser is the problem.

Warum nutzen

Hauptfunktionen

Live-Demo

In der Praxis

browser-tools.replay ▶ bereit
0/0

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "browser-tools": {
      "command": "npx",
      "args": [
        "-y",
        "@agentdeskai/browser-tools-mcp@latest"
      ]
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "browser-tools": {
      "command": "npx",
      "args": [
        "-y",
        "@agentdeskai/browser-tools-mcp@latest"
      ]
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "browser-tools": {
      "command": "npx",
      "args": [
        "-y",
        "@agentdeskai/browser-tools-mcp@latest"
      ]
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "browser-tools": {
      "command": "npx",
      "args": [
        "-y",
        "@agentdeskai/browser-tools-mcp@latest"
      ]
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "browser-tools",
      "command": "npx",
      "args": [
        "-y",
        "@agentdeskai/browser-tools-mcp@latest"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json
{
  "context_servers": {
    "browser-tools": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "@agentdeskai/browser-tools-mcp@latest"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add browser-tools -- npx -y @agentdeskai/browser-tools-mcp@latest

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: Browser Tools

Debug a live front-end bug using real console + network context

👤 Frontend engineers ⏱ ~15 min intermediate

Wann einsetzen: A bug only reproduces in your actual session (logged in, specific data). You want the agent to read the console and network tab.

Voraussetzungen
  • Chrome extension installed + bridge server running — Install extension from releases page, then npx @agentdeskai/browser-tools-server@latest in a terminal
  • MCP server wired to your clientnpx -y @agentdeskai/browser-tools-mcp@latest
Ablauf
  1. Reproduce the bug with DevTools open
    Open the affected page in Chrome with the extension active. Trigger the bug. Don't close the tab.✓ Kopiert
    → Bug visible, extension icon shows it's capturing
  2. Pull context into the agent
    Get the last 50 console messages and any failed network requests. Summarize what the page is yelling about.✓ Kopiert
    → Specific errors surfaced with stack traces
  3. Diagnose and propose fix
    Based on the errors, point at the file/line likely responsible. If 404s, identify the bad URL; if JS errors, the root cause.✓ Kopiert
    → Concrete hypothesis with evidence

Ergebnis: A debugging loop where the agent has the same context as you opening DevTools — faster than reading a screenshot description.

Fallstricke
  • Bridge server not running, MCP silently returns empty data — Always check curl localhost:3025/identity responds first; the bridge must be running before the MCP call
  • Capturing from the wrong tab — Extension captures the active tab. Click into the right tab before asking the agent
Kombinieren mit: sentry

Run a Lighthouse-style audit on the page you're looking at

👤 Frontend / SEO / a11y engineers ⏱ ~10 min beginner

Wann einsetzen: You want to audit a page as it actually renders in your session (not a clean crawler).

Ablauf
  1. Open the target page
    Navigate to <URL> in Chrome with the extension active.✓ Kopiert
    → Page loaded
  2. Run the audit mode
    Run the audit tool — perf, a11y, SEO, best practices. Summarize top 5 issues with fix suggestions.✓ Kopiert
    → Prioritized issue list
  3. Focus in
    For the accessibility failures, list exact selectors and the WCAG rule violated.✓ Kopiert
    → Actionable remediation steps

Ergebnis: A full audit without leaving your browser, scoped to real user state.

Fallstricke
  • Audits for auth-gated pages fail because the tool re-navigates — Use the debugger mode's element/console tools on the already-loaded page instead of the full audit

Inspect and explain a specific element

👤 Frontend devs, designers ⏱ ~5 min beginner

Wann einsetzen: Something looks off in one component. You want a quick 'what CSS is applied and why' without digging.

Ablauf
  1. Select the element in DevTools
    Open DevTools, click the element inspector, select the offending element.✓ Kopiert
    → Element highlighted in Elements panel
  2. Ask the agent to inspect
    Get the selected element's computed styles, inherited rules, and bounding box. Explain why it's rendering the way it is.✓ Kopiert
    → Explanation grounded in actual CSS cascade
  3. Propose a fix
    Suggest the smallest CSS change to achieve [desired visual]. Show the before/after rule.✓ Kopiert
    → Minimal diff suggestion

Ergebnis: CSS debugging at conversation speed.

Fallstricke
  • Element selection doesn't persist — agent sees a different one — Re-select the element right before asking; don't let the DevTools panel change focus between messages

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

browser-tools + sentry

Reproduce a Sentry error in YOUR browser and pull live console context

Sentry issue WEB-3a91 says an XHR to /api/checkout returns 500. Navigate to the page in my Chrome, reproduce, and capture the console + network.✓ Kopiert
browser-tools + playwright

browser-tools for live debugging, Playwright for repeatable reproductions afterward

I found the bug in my live Chrome via browser-tools. Now write a Playwright test that reproduces the exact click sequence.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

WerkzeugEingabenWann aufrufenKosten
takeScreenshot Visual capture of current state free
getConsoleLogs / getConsoleErrors Debug any JS error free
getNetworkLogs / getNetworkErrors Diagnose failed API calls free
getSelectedElement User has selected an element in DevTools free
runAccessibilityAudit A11y review of current page free
runPerformanceAudit Perf audit of current page free
runSEOAudit SEO review free
runBestPracticesAudit General code quality review free
runNextJSAudit You're on Next.js free
wipeLogs Clear between investigation sessions free

Kosten & Limits

Was der Betrieb kostet

API-Kontingent
None — all local
Tokens pro Aufruf
Log dumps can be big (5k+ tokens). Use wipeLogs between sessions.
Kosten in €
Free, open source
Tipp
Wipe logs before each investigation — avoids pulling in unrelated noise

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: None — runs against your existing Chrome session
Datenabfluss: Only to localhost:3025 (the bridge). Nothing leaves your machine except via whatever the agent/MCP client does.

Fehlerbehebung

Häufige Fehler und Lösungen

All tools return empty / 'not connected'

The bridge server isn't running. Start it: npx @agentdeskai/browser-tools-server@latest in a dedicated terminal.

Prüfen: curl http://localhost:3025/identity
Extension icon grey / inactive

Click the extension icon, confirm it says 'Connected'. If not, reload the tab.

Audits fail with timeout

Some audits need extra time on heavy pages. Close other tabs to free CPU; re-run.

Wrong tab captured

The extension captures the tab that was last activated. Click into the right tab immediately before calling a tool.

Alternativen

Browser Tools vs. andere

AlternativeWann stattdessenKompromiss
chrome-devtools MCPYou want direct CDP access without a browser extensionNo extension needed but you lose real-user-session context
Playwright MCPYou need repeatable automation, not live debuggingClean browser — can't see your logged-in session

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen