Esta página se muestra en inglés. Una traducción al español está en curso.
MCP ConfigsMay 14, 2026·2 min de lectura

BrowserToolsMCP — Audit Browser Logs via MCP

BrowserToolsMCP streams browser logs to MCP clients: install via `npx`, run a local server, and audit network/console events from your IDE (7.2k★).

MCP Hub
MCP Hub · Community
Listo para agents

Este activo puede ser leído e instalado directamente por agents

TokRepo expone un comando CLI universal, contrato de instalación, metadata JSON, plan según adaptador y contenido raw para que los agents evalúen compatibilidad, riesgo y próximos pasos.

Native · 94/100Política: permitir
Superficie agent
Cualquier agent MCP/CLI
Tipo
Mcp
Instalación
Bundle
Confianza
Confianza: Established
Entrada
npx @agentdeskai/browser-tools-mcp@latest
Comando CLI universal
npx tokrepo install 80bc9d31-f1e5-5528-8e4b-bc93fe9b1d88
contrato de instalaciónJSON de metadataplan adaptadorcontenido raw
Introducción

BrowserToolsMCP streams browser logs to MCP clients: install via npx, run a local server, and audit network/console events from your IDE (7.2k★).

Best for: Debugging agent-driven browser automation (Playwright, extension flows) when you need visibility into console/network signals

Works with: MCP-compatible IDE clients, Chrome/Chromium, and a separate terminal for browser-tools-server as described in the README

Setup time: 8-20 minutes

Main

  • Two-part architecture: the README separates the IDE-side MCP server from the standalone browser-tools-server, which keeps logs flowing even when your IDE restarts.
  • Audit-first workflow: explicitly designed for auditing (network + console) so you can debug “why did the agent do that” issues.
  • IDE friendly: you install the MCP side inside your IDE and keep the server in a separate terminal—simple operational model.
  • Release-tracked extension: provides a versioned Chrome extension zip in GitHub releases, making installs reproducible.

FAQ

  • Do I need the extension?: Yes. The quickstart requires installing the Chrome extension so the server can receive logs.
  • Why run a separate server?: It keeps the log pipeline stable and avoids coupling log collection to your IDE process.
  • How do I start safely?: Install first, then run audits on a simple page to confirm you see console + network events.
🙏

Fuente y agradecimientos

Source: https://github.com/AgentDeskAI/browser-tools-mcp > License: MIT > GitHub stars: 7212 · forks: 521

Discusión

Inicia sesión para unirte a la discusión.
Aún no hay comentarios. Sé el primero en compartir tus ideas.

Activos relacionados

Playwright MCP — Browser Automation for Agents

Playwright MCP exposes browser automation via MCP with device emulation; verified 5,510★ and documents 143 device profiles plus `playwright install` setup.

MCP Configs
MCP Hub

kubernetes-mcp-server — Kubernetes Tools via MCP

kubernetes-mcp-server exposes Kubernetes operations to MCP clients with npx/uvx/binary run modes; verified 1584★ and pushed 2026-05-14.

MCP Configs
MCP Hub

SigNoz MCP Server — Query Traces, Logs & Alerts

SigNoz MCP Server connects MCP clients to your SigNoz instance: query traces/logs, inspect alerts, and automate observability workflows using an API key.

MCP Configs
MCP Hub

Playwright MCP — Browser Automation Server

Playwright MCP is an MCP server for browser automation via Playwright snapshots. Add via npx in Claude Code/Codex to run deterministic actions.

MCP Configs
MCP Hub
◈Inicio🔍Buscar👤Yo