Eine Automatisierungs-Engine, mit der KI-Agenten Live-Chromium-Browser und Electron-Desktop-Anwendungen lokal über CDP-Sockets steuern können.
Auch bekannt als Weavetab/mcp, mcp, @weavetab/mcp
- Stars
- 3
- Tools
- —
- Downloads, 30 Tage
- —
- Neueste Version
- 2.5.0
- Letzter Commit
- 7. Nov. 2026
- Lizenz
- AGPL-3.0
Was ist Weavetab MCP?
Eine Automatisierungs-Engine, mit der KI-Agenten Live-Chromium-Browser und Electron-Desktop-Anwendungen lokal über CDP-Sockets steuern können.
Zusammenfassung generiert aus dem README des Projekts
Über Weavetab MCP server
Weavetab bietet eine Automatisierungs-Engine, die speziell dafür entwickelt wurde, dass KI-Agenten mit Live-Chromium-Browsern und Electron-Desktop-Anwendungen interagieren können. Durch die direkte Verbindung zu lokalen Chrome DevTools Protocol Sockets entfällt der Overhead von WebDriver-Binaries oder Cloud-Relays. Dies ermöglicht eine extrem schnelle Ausführung von Aufgaben in lokalen Umgebungen und unterstützt Anwendungen wie Discord, VS Code oder Figma über registrierte Electron-Prozesse.
Entwickler können diesen Server über stdio oder einen lokalen WebSocket-Daemon in MCP-Clients wie Claude Desktop, Cursor oder Windsurf integrieren. Das System nutzt Semantic Map 3.0, um Webseiten in kompakte, agentenlesbare Formate zu übersetzen, was den Token-Verbrauch durch Delta-Diffing um bis zu 95 % reduziert. Die Sicherheit wird lokal über Domain-Policies, rollenbasierte Zugriffskontrolle und ein Blind-Injection-System gewährleistet, das verhindert, dass sensible Zugangsdaten jemals in den LLM-Kontext gelangen.
Über die Standard-Webnavigation hinaus umfasst das Toolset spezialisierte Funktionen wie Ghost Cursor für menschenähnliche Mausbewegungen und einen Zero-API-Ansatz zur Lösung von CAPTCHAs. Es ist für Nutzer konzipiert, die High-Fidelity-Automatisierung mit strengem Datenschutz und geringer Latenz benötigen.
Was du damit machen kannst
- 1Desktop-Anwendungs-Workflows automatisierenEin Agent kann Aktionen innerhalb installierter Desktop-Software wie Discord oder VS Code ausführen, indem Befehle direkt an den spezifischen Electron-Prozess geroutet werden.
- 2Sensible Zugangsdaten sicher handhabenDu kannst eine KI anweisen, sich bei Diensten anzumelden, ohne dass das Modell das eigentliche Passwort oder den Token jemals zu Gesicht bekommt.
- 3Bot-Detection-Mechanismen umgehenDie Engine kann komplexe CAPTCHAs navigieren, indem sie menschliche physische Mausbewegungen und Beschleunigungen imitiert.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du Weavetab MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenWeavetab MCP in Claude Code installieren
$ claude mcp add mcp -- npx -y @weavetab/mcpWeavetab MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@weavetab/mcp"
]
}
}
}Weavetab MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@weavetab/mcp"
]
}
}
}Weavetab MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"mcp","type":"stdio","command":"npx","args":["-y","@weavetab/mcp"]}'Weavetab MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@weavetab/mcp"
]
}
}
}Weavetab MCP in Codex installieren
$ codex mcp add mcp -- npx -y @weavetab/mcpWeavetab MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.mcp] command = "npx" args = ["-y", "@weavetab/mcp"]
Weavetab MCP in Gemini CLI installieren
$ gemini mcp add -s user mcp npx -- -y @weavetab/mcpWeavetab MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@weavetab/mcp"
]
}
}
}Automatisierte Checks
Geluften am 14. Nov. 2026Vollständiger Bericht →Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren
- Source Repository verknüpft und erreichbarweavetab/mcp is public and reachablegithub.com/weavetab/mcp ↗Bestanden
- Paket nennt dieses Repository als Quelle@weavetab/mcp names weavetab/mcp as sourcenpmjs.com/package/@weavetab/mcp ↗Bestanden
- Build-Provenienz (Sigstore-Attestierung)No build attestation published for this releaseNicht geprüft
- Open Source Lizenz (OSI)AGPL-3.0spdx.org/licenses/AGPL-3.0.html ↗Bestanden
- Commit oder Release im letzten JahrLast commit or release 2026-11-07github.com/weavetab/mcp ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNo popular package one edit away from @weavetab/mcpBestanden
- Keine kritischen Advisories im Paket oder seinen Abhängigkeiten264 resolved dependencies checked; no critical advisoryosv.dev ↗Bestanden
- Keine versteckten Anweisungen an das Modell0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNicht geprüft
- Remote-Endpoint beantwortet den MCP-HandshakeNicht geprüft
README
Auf GitHub ansehenWeavetab 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.
Weavetab MCP Fragen
Wie füge ich Weavetab MCP zu Claude Code hinzu?
Führe claude mcp add mcp -- npx -y @weavetab/mcp in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich Weavetab MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Wie unterscheidet sich Weavetab von Playwright oder Puppeteer?
Im Gegensatz zu Standardansätzen nutzt Weavetab direkte CDP-WebSocket-Verbindungen für geringeren Overhead, unterstützt Electron-Desktop-Apps und verwendet Semantic Map 3.0, um den Token-Verbrauch um bis zu 95 % zu senken.
Kann Weavetab Desktop-Anwendungen steuern?
Ja, es kann jede Electron-basierte Anwendung wie Discord, VS Code oder Figma steuern, indem der Anwendungspfad in der Config registriert wird.
Wie werden sensible Zugangsdaten gehandhabt?
Es nutzt Blind Injection, bei der Secrets serverseitig aufgelöst werden und niemals im LLM-Kontext, in DOM-Snapshots oder in Audit-Logs auftauchen.
Benötigt es externe Dienste, um CAPTCHAs zu lösen?
Nein, es löst CAPTCHAs, indem es menschliche Verhaltenssignaturen durch CDP-Mouse-Events repliziert, ohne dass Drittanbieter-APIs erforderlich sind.