swarmclaw MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

23+ LLM provider integrations under one roof
Delegates to Claude Code, Codex, OpenCode, native subagents
Memory: hybrid recall + graph traversal + durable docs
Schedules, background jobs, heartbeat loops for long-running autonomy

Live-Demo

In der Praxis

swarmclaw.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": {
    "swarmclaw": {
      "command": "npx",
      "args": [
        "-y",
        "swarmclaw"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "swarmclaw": {
      "command": "npx",
      "args": [
        "-y",
        "swarmclaw"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "swarmclaw": {
      "command": "npx",
      "args": [
        "-y",
        "swarmclaw"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "swarmclaw": {
      "command": "npx",
      "args": [
        "-y",
        "swarmclaw"
      ],
      "_inferred": true
    }
  }
}

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

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "swarmclaw",
      "command": "npx",
      "args": [
        "-y",
        "swarmclaw"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "swarmclaw": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "swarmclaw"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add swarmclaw -- npx -y swarmclaw

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

Anwendungsfälle

Praxisnahe Nutzung: swarmclaw

Run an always-on research agent with SwarmClaw

👤 Researchers, competitive-intel analysts ⏱ ~45 min advanced

Wann einsetzen: You want an agent that wakes up daily, runs a research loop, and drops results somewhere.

Voraussetzungen

SwarmClaw installed — One-click desktop installer or npm i -g @swarmclawai/swarmclaw
First-run access key — Generated on initial launch at http://localhost:3456

Ablauf

Define the agent

Create a SwarmClaw agent 'daily-ai-news' with provider=Claude, memory=enabled, schedule='every day 08:00'.✓ Kopiert

→ Agent registered
Attach tools via MCP

Attach firecrawl + notion MCPs so the agent can scrape and write results to Notion.✓ Kopiert

→ Tools wired
Let it run

Enable the schedule. Review memory weekly to see what it's learned.✓ Kopiert

→ Daily Notion pages appear

Ergebnis: A background research teammate.

Fallstricke

LLM cost spiral on long loops — Set per-session token budgets in the agent config; alert on overrun

Kombinieren mit: firecrawl

Delegate coding tasks across multiple models with SwarmClaw

👤 Engineers who want quality-vs-speed tradeoffs per sub-task ⏱ ~60 min advanced

Wann einsetzen: A feature has planning (Opus), bulk coding (Sonnet), and polish (Codex) phases.

Ablauf

Define the pipeline

Create a workflow: planner=Claude Opus, coder=Claude Sonnet via Claude Code, reviewer=Codex. Handoffs via transcript.✓ Kopiert

→ Workflow visible in UI
Run on a task

Run the workflow on feature spec [paste]. Watch the handoffs.✓ Kopiert

→ Final PR proposal after each stage contributes

Ergebnis: Right tool for each phase of a single feature.

Kombinieren mit: github

Build a memory-rich personal assistant with SwarmClaw

👤 Power users who dislike re-explaining context each session ⏱ ~30 min intermediate

Wann einsetzen: Your ChatGPT/Claude sessions lose context you wanted retained across days.

Ablauf

Enable hybrid memory

Create a long-lived session 'assistant' with hybrid memory (vector + graph). Pipe all prior transcripts into the memory.✓ Kopiert

→ Memory populated
Ask and let it recall

What were my open questions from last Tuesday's session about pricing?✓ Kopiert

→ Recalled items with citations to source sessions

Ergebnis: An assistant that actually remembers.

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

swarmclaw + claude-code

SwarmClaw orchestrates; Claude Code is the coder in the loop

Delegate the 'implement-feature' step to Claude Code via the swarmclaw workflow.✓ Kopiert

swarmclaw + firecrawl

Scheduled scraping + memory-enriched analysis

Daily agent: scrape competitor pages, diff against memory, flag changes.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
create_agent	name, provider, memory?, schedule?	Bootstrap a new agent	0
attach_mcp	agent_id, mcp_config	Give the agent tools	0
run_session	agent_id, input	Ad-hoc invocation	LLM tokens
schedule_agent	agent_id, cron	Long-running autonomy	0
memory_query	agent_id, query	Inspect agent memory	0

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: Whatever your LLM providers enforce
Tokens pro Aufruf: Multi-turn sessions with memory retrieval: 3-30k per step
Kosten in €: Free self-hosted; LLM token costs are yours
Tipp: Set hard per-session budgets; autonomous loops can spend unnoticed

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: LLM keys encrypted in the local data dir; first-run access key protects the UI

Datenabfluss: To each configured LLM provider + attached MCPs

Niemals gewähren: internet-exposing the UI without auth — default is localhost only

Fehlerbehebung

Häufige Fehler und Lösungen

UI inaccessible after install

SwarmClaw binds to 127.0.0.1:3456; ensure nothing else owns that port. lsof -i :3456

Agent loops spend tokens in the background

Disable its schedule and inspect last transcripts; set a token budget on the agent before re-enabling

MCP server fails to start under swarmclaw

Test the MCP command manually first (with f/mcptools); swarmclaw uses the same invocation

Prüfen: mcp tools -- <your-mcp-cmd>

Alternativen

swarmclaw vs. andere

Alternative	Wann stattdessen	Kompromiss
n8n-workflow-builder	You want deterministic workflow automation not agent loops	Less agentic; no LLM memory
LangGraph / Autogen	You want code-first orchestration in your own app	You host + write everything

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen