swarmclaw MCP — Use Cases, Install & Live Demo

Why use it

Key features

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

What it looks like in practice

swarmclaw.replay ▶ ready

0/0

Install

Pick your 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
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

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

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

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

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

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

Add to context_servers. Zed hot-reloads on save.

claude mcp add swarmclaw -- npx -y swarmclaw

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use swarmclaw

Run an always-on research agent with SwarmClaw

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

When to use: You want an agent that wakes up daily, runs a research loop, and drops results somewhere.

Prerequisites

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

Flow

Define the agent

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

→ Agent registered
Attach tools via MCP

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

→ Tools wired
Let it run

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

→ Daily Notion pages appear

Outcome: A background research teammate.

Pitfalls

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

Combine with: firecrawl

Delegate coding tasks across multiple models with SwarmClaw

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

When to use: A feature has planning (Opus), bulk coding (Sonnet), and polish (Codex) phases.

Flow

Define the pipeline

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

→ Workflow visible in UI
Run on a task

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

→ Final PR proposal after each stage contributes

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

Combine with: github

Build a memory-rich personal assistant with SwarmClaw

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

When to use: Your ChatGPT/Claude sessions lose context you wanted retained across days.

Flow

Enable hybrid memory

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

→ Memory populated
Ask and let it recall

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

→ Recalled items with citations to source sessions

Outcome: An assistant that actually remembers.

Combinations

Pair with other MCPs for X10 leverage

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.✓ Copied

swarmclaw + firecrawl

Scheduled scraping + memory-enriched analysis

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

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
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

Cost & Limits

What this costs to run

API quota: Whatever your LLM providers enforce
Tokens per call: Multi-turn sessions with memory retrieval: 3-30k per step
Monetary: Free self-hosted; LLM token costs are yours
Tip: Set hard per-session budgets; autonomous loops can spend unnoticed

Security

Permissions, secrets, blast radius

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

Data egress: To each configured LLM provider + attached MCPs

Never grant: internet-exposing the UI without auth — default is localhost only

Troubleshooting

Common errors and fixes

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

Verify: mcp tools -- <your-mcp-cmd>

Alternatives

swarmclaw vs others

Alternative	When to use it instead	Tradeoff
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

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills