Un motor de automatización que permite a los agentes de IA controlar navegadores Chromium en vivo y aplicaciones de escritorio Electron localmente a través de sockets CDP.
También conocido como Weavetab/mcp, mcp, @weavetab/mcp
- Stars
- 3
- Herramientas
- —
- Descargas, 30 días
- —
- Última versión
- 2.5.0
- Último commit
- 7 nov 2026
- Licencia
- AGPL-3.0
¿Qué es Weavetab MCP?
Un motor de automatización que permite a los agentes de IA controlar navegadores Chromium en vivo y aplicaciones de escritorio Electron localmente a través de sockets CDP.
Resumen generado a partir del README del proyecto
Acerca del MCP server de Weavetab
Weavetab proporciona un motor de automatización diseñado para que los agentes de IA interactúen con navegadores Chromium en vivo y aplicaciones de escritorio Electron. Al conectarse directamente a sockets locales del Chrome DevTools Protocol, evita la sobrecarga de los binarios de WebDriver o los relays en la nube. Esto permite una ejecución de tareas a alta velocidad dentro de entornos locales, soportando aplicaciones como Discord, VS Code o Figma a través de procesos Electron registrados.
Los desarrolladores pueden integrar este servidor en clientes MCP como Claude Desktop, Cursor o Windsurf utilizando stdio o un demonio WebSocket local. El sistema utiliza Semantic Map 3.0 para traducir páginas web a formatos compactos legibles por agentes, lo que reduce el consumo de tokens hasta en un 95% mediante delta diffing. La seguridad se gestiona localmente a través de políticas de dominio, control de acceso basado en roles y un sistema de blind injection que evita que las credenciales sensibles entren en el contexto del LLM.
Más allá de la navegación web estándar, el conjunto de herramientas incluye capacidades especializadas como Ghost Cursor para movimientos de ratón similares a los humanos y un enfoque de cero APIs para resolver CAPTCHAs. Está diseñado para usuarios que requieren una automatización de alta fidelidad con privacidad estricta y baja latencia.
Qué puedes hacer con él
- 1Automatizar flujos de trabajo en aplicaciones de escritorioUn agente puede realizar acciones dentro de software de escritorio instalado como Discord o VS Code enviando comandos al proceso Electron específico.
- 2Gestionar credenciales sensibles de forma seguraPuedes instruir a una IA para que inicie sesión en servicios sin que el modelo llegue a ver la contraseña o el token real.
- 3Evadir mecanismos de detección de botsEl motor puede navegar a través de CAPTCHAs complejos imitando los movimientos físicos y la aceleración del ratón humano.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Cómo instalar Weavetab MCP
Formatos verificados el 10 nov 2026Añadir a CursorAñadir a GooseInstalar Weavetab MCP en Claude Code
$ claude mcp add mcp -- npx -y @weavetab/mcpInstalar Weavetab MCP en Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@weavetab/mcp"
]
}
}
}Instalar Weavetab MCP en VS Code
.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@weavetab/mcp"
]
}
}
}Instalar Weavetab MCP en VS Code CLI
$ code --add-mcp '{"name":"mcp","type":"stdio","command":"npx","args":["-y","@weavetab/mcp"]}'Instalar Weavetab MCP en Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@weavetab/mcp"
]
}
}
}Instalar Weavetab MCP en Codex
$ codex mcp add mcp -- npx -y @weavetab/mcpInstalar Weavetab MCP en Codex config.toml
~/.codex/config.toml
[mcp_servers.mcp] command = "npx" args = ["-y", "@weavetab/mcp"]
Instalar Weavetab MCP en Gemini CLI
$ gemini mcp add -s user mcp npx -- -y @weavetab/mcpInstalar Weavetab MCP en Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@weavetab/mcp"
]
}
}
}Verificaciones automáticas
Ejecutado 14 nov 2026Informe completo →Pasó nuestras verificaciones automáticas. Esto no es una auditoría de seguridad: lee el código y dale al servidor el acceso más limitado que necesite. Cómo funcionan las verificaciones
- Repositorio de origen vinculado y accesibleweavetab/mcp is public and reachablegithub.com/weavetab/mcp ↗Aprobado
- El paquete indica este repositorio como su origen@weavetab/mcp names weavetab/mcp as sourcenpmjs.com/package/@weavetab/mcp ↗Aprobado
- Procedencia de la compilación (atestación de Sigstore)No build attestation published for this releaseNo verificado
- Licencia de código abierto (OSI)AGPL-3.0spdx.org/licenses/AGPL-3.0.html ↗Aprobado
- Commit o lanzamiento en el último añoLast commit or release 2026-11-07github.com/weavetab/mcp ↗Aprobado
- OpenSSF ScorecardNo verificado
- El nombre del paquete no es similar a un paquete popularNo popular package one edit away from @weavetab/mcpAprobado
- No hay avisos críticos en el paquete ni en sus dependencias264 resolved dependencies checked; no critical advisoryosv.dev ↗Aprobado
- Sin instrucciones ocultas para el modelo0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersAprobado
- Las herramientas destructivas están etiquetadasNo verificado
- El endpoint remoto responde al handshake de MCPNo verificado
README
Ver en GitHubWeavetab is the open automation engine for AI agents. It connects models directly to live Chromium browsers and Electron desktop applications via native Chrome DevTools Protocol (CDP) sockets — no WebDriver binaries, no cloud relay, zero telemetry.
Actions execute directly over local CDP sockets without external driver overhead. Web pages are translated into agent-readable semantic maps with turn-by-turn diffing that reduces token usage by up to 95%. Built-in security enforces local domain policies, role-based access control, and client-side credential injection.
Built by Weavetab, architected by fy2ne.
Why not Playwright or Puppeteer?
The standard approach — Playwright over MCP — works. But it carries fundamental architectural costs that compound at scale.
| Playwright / Puppeteer | Weavetab | |
|---|---|---|
| Protocol layer | WebDriver BiDi or CDP via browser binary | Direct CDP WebSocket |
| Tool execution overhead | 50–300 ms (binary + IPC overhead) | In-process (direct local socket) |
| Desktop app control | Browser only | Chrome + any Electron app (Discord, VS Code, Figma…) |
| DOM representation | Full HTML dump to LLM | Semantic Map 3.0 with delta diffing |
| Token cost per map | ~2,000–8,000 tokens | ~80–400 tokens (95% reduction via delta) |
| CAPTCHA | API service required | Zero-API via CDP mouse physics |
| Credential safety | Secrets passed in plaintext | Blind Injection — never in LLM context |
| Extension access | Limited | Full Chrome Extension API surface |
Architecture
MCP Client (Claude / Cursor / Antigravity / Copilot / Windsurf)
|
| JSON-RPC 2.0 (stdio or WebSocket 127.0.0.1:3000)
v
+-------------------------------------------------------------+
| Weavetab MCP Server |
| |
| +-----------------+ +---------------------------------+ |
| | Security Layer |-->| Intelligence Engine | |
| | Rate · RBAC | | Map 3.0 · Delta · Memory | |
| | Policy · Audit | | Pruner · Framework Detector | |
| +-----------------+ +----------------+----------------+ |
| | |
| +----------v----------------+ |
| | CDP Bridge | |
| | Ghost Cursor · Typing | |
| | App Router · Loop Guard | |
| +----------+----------------+ |
+-------------------------------------------------------------+
| CDP WebSocket (127.0.0.1)
+---------------------------+-----------------------------+
v v v
Chrome / Edge VS Code / Discord Your Electron App
(any tab) (Electron apps) (local dev)
No cloud. No external process. Both the CDP WebSocket connection and the optional MCP WebSocket daemon (--ws) are strictly bound to 127.0.0.1 with shared-secret authentication (~/.weavetab-system/ws-secret) and Origin/Host header verification.
Quick Start
npx -y @weavetab/mcp
Add to your MCP client config:
{
"mcpServers": {
"weavetab": {
"command": "npx",
"args": ["-y", "@weavetab/mcp"]
}
}
}
| Client | Config path |
|---|---|
| Claude Desktop | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Claude Code | claude mcp add weavetab -- npx -y @weavetab/mcp |
| Cursor | .cursor/mcp.json |
| Antigravity | ~/.gemini/antigravity/mcp/weavetab/ |
| VS Code Copilot | .vscode/mcp.json |
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
Core Technology
Semantic Map 3.0
The primary bottleneck in browser-based agents is DOM representation. Full HTML dumps are noisy, large, and structurally meaningless to language models. Weavetab's browser_map runs an in-browser CDP walker that produces a compact semantic map:
╔═ ACTIVE DIALOG: "Confirm Payment" ═╗
[w:3] button "Confirm" [w:4] button "Cancel"
┌ "Pro Plan — $49/mo"
[w:12] button "Upgrade" [w:13] button "View Details"
[w:14] input val:"john@example.com" ph:"Email address" FOCUSED
[w:20...w:38] 18 nav links: "Dashboard" ... "Sign out"
Key properties:
- Ref IDs (
w:N) are stable within a session and used by all interaction tools - Container binding — buttons and inputs are grouped under their parent card, row, or section header
- Modal hoisting — open dialogs are isolated at the top so agents cannot miss them
- Link collapsing — repeated nav/footer runs of 4+ links compress into a single token line
- Semantic delta — on re-reads, only changed nodes are transmitted (
~modified,+added,−removed), cutting re-read cost by up to 95%
Ghost Cursor
Clicks are not dispatched as synthetic DOM events. They are delivered as a physical sequence of Input.dispatchMouseEvent CDP calls along a Bezier curve trajectory with randomized acceleration, natural jitter, and hold durations. Anti-bot fingerprinting that flags event-based automation does not trigger.
browser_pointer supports hover_chain for multi-level menu traversal in a single tool call:
{
"hover_chain": ["File", "Export As", "PNG"],
"click_final": true
}
Blind Credential Injection
browser_type_secret resolves secrets server-side from ~/.weavetab/secrets.json. The resolved value is never included in the MCP response, never appears in DOM snapshots, and is permanently masked as [REDACTED] in all audit logs. The LLM context never sees the credential.
weavetab secrets set GITHUB_TOKEN
# Stored. Never echoed, never logged, never surfaced to the agent.
Electron & Desktop App Automation
Any tool accepts an optional app parameter that routes the command to a registered Electron process instead of a browser tab:
{ "app": "discord", "ref": "w:24", "text": "Hey, deploying now" }
Register apps in ~/.weavetab/config.json:
{
"electron": {
"discord": "C:\\Users\\<user>\\AppData\\Local\\Discord\\Discord.exe",
"vscode": "C:\\Users\\<user>\\AppData\\Local\\Programs\\Microsoft VS Code\\Code.exe",
"figma": "C:\\Users\\<user>\\AppData\\Local\\Figma\\Figma.exe"
}
}
Weavetab auto-attaches via CDP to the registered process. No code changes required in the target application.
Zero-API CAPTCHA Solving
browser_captcha solves Cloudflare Turnstile, reCAPTCHA v2/v3, GeeTest, and hCaptcha by orchestrating CDP mouse events that replicate human behavioral signatures — velocity curves, micro-pauses, scroll inertia — with no third-party API, no external service, and no API key required.
Tool Suite
41 tools across 9 categories. Full parameter reference: docs/tools/tools.md
| Category | Tools |
|---|---|
| Vision & DOM | browser_map browser_find browser_scrape browser_inspect browser_snapshot browser_screenshot browser_console browser_extract_design |
| Input & Interaction | browser_click browser_type browser_type_secret browser_key browser_pointer browser_select browser_fill browser_upload browser_scroll |
| Navigation & Environment | browser_navigate browser_tabs browser_detect browser_viewport browser_emulate |
| Mission & Automation | browser_burst browser_automation browser_recording browser_pattern_learn |
| Safety & Human Oversight | browser_dialog browser_thoughts browser_clipboard browser_wait |
| Autonomous CAPTCHA | browser_captcha |
| Network & Storage | browser_network_intercept browser_storage browser_cookies browser_checkpoint browser_performance |
| Office Documents | browser_office |
| Canvas & Eval | browser_eval browser_pdf browser_canvas browser_highlight |
Security
- Transport: Both CDP WebSocket and MCP WebSocket daemon (
--ws) are strictly bound to127.0.0.1with 256-bit shared-secret Bearer/handshake authentication andOrigin/Hostvalidation. No listener on external interfaces. - Policy Engine: Per-domain
allow/read-only/deny/auditrules under the top-levelpoliciesarray in~/.weavetab/config.json(blocks*.bank.*andpaypal.comout of the box) - RBAC: Five roles —
operator(default),viewer(least-privilege read-only),automation,system,admin— enforce tool-level permission gates - Plugin Trust & Manifests: 3-tier verification (
@weavetab/*official, verified registry allowlist, and mandatory interactive confirmation +weavetab.jsonpermission manifest inspection for unverified packages) - Blind Injection: Credentials resolved server-side, masked in all outputs and audit logs
- Loop Breaker: Strike-based stuck-loop detector halts runaway autonomous sequences
- Audit Log: All tool invocations, policy decisions, and errors written to
~/.weavetab-system/logs/mission_<timestamp>.log
Security vulnerabilities: security@weavetab.dev (do not use public issues).
CLI Reference
weavetab # Start in stdio mode (default)
weavetab --ws --port 3000 # WebSocket daemon mode (bound to 127.0.0.1)
weavetab config # Interactive configuration wizard
weavetab secrets set KEY_NAME # Store a secret (never echoed)
weavetab secrets list # List stored secret keys (not values)
weavetab plugin add <name> # Install a verified/confirmed plugin
weavetab plugin update <name> # Interactively upgrade an installed plugin
weavetab plugin list # List installed plugins
Configuration file: ~/.weavetab/config.json
{
"browserType": "chromium",
"headless": false,
"extension": true,
"maxActionsPerMinute": 60,
"role": "operator",
"electron": {
"discord": "...",
"vscode": "...",
"antigravity": "..."
}
}
Extensibility
Weavetab exposes a typed Plugin SDK for authoring custom MCP tools, HUD overlays, and tool lifecycle hooks:
npx @weavetab/sdk init my-plugin
See docs/PLUGINS.md for architecture, manifest spec, and SDK API reference.
License
AGPL-3.0-only. Client connections over stdio or WebSocket do not extend copyleft obligations to your client application or models.
For commercial embedding, closed-source SaaS, or proprietary enterprise licensing, see COMMERCIAL.md or contact license@weavetab.dev.
Preguntas sobre Weavetab MCP
¿Cómo agrego Weavetab MCP a Claude Code?
Ejecuta claude mcp add mcp -- npx -y @weavetab/mcp en tu terminal. Añade --scope user para que esté disponible en todos los proyectos.
¿Cómo agrego Weavetab MCP a Cursor?
Abre ~/.cursor/mcp.json y añade el servidor en mcpServers, usando la configuración de Cursor que se muestra en la sección de instalación de arriba.
¿En qué se diferencia Weavetab de Playwright o Puppeteer?
A diferencia de los enfoques estándar, Weavetab utiliza conexiones directas de WebSocket vía CDP para reducir la sobrecarga, es compatible con aplicaciones de escritorio Electron y utiliza Semantic Map 3.0 para reducir el uso de tokens hasta en un 95%.
¿Puede Weavetab controlar aplicaciones de escritorio?
Sí, puede controlar cualquier aplicación basada en Electron como Discord, VS Code o Figma registrando la ruta de la aplicación en la configuración.
¿Cómo gestiona las credenciales sensibles?
Utiliza Blind Injection, donde los secretos se resuelven en el lado del servidor y nunca se incluyen en el contexto del LLM, en los snapshots del DOM ni en los registros de auditoría.
¿Requiere servicios externos para resolver CAPTCHAs?
No, resuelve los CAPTCHAs replicando firmas de comportamiento humano mediante eventos de ratón de CDP sin necesidad de APIs de terceros.