// teleport guide · Infra · community

Teleport Docker MCP — read-only, P2P, zero cloud

Docker's official MCP server controls the Docker daemon on the host machine. Sharing it raw would let a foreign LLM start or stop anything you run. Teleport the observability tools only — container logs and image listings — and keep lifecycle control local. This guide maps all 8 tools of docker/mcp-server-docker by blast radius, then gives you the exact command to share it with a remote teammate's AI agent — capability without credentials.

3SAFE to expose

1CAUTION

4KEEP LOCAL

0servers involved

host terminal — read-only share command

npx -y mcpwire share --allow "list_containers,list_images,inspect_container" --redact-secrets --ttl 30m -- docker run -i --rm docker/mcp-server-docker

Only the 3 read-only tools are exposed; the other 5 are invisible to the peer (filtered from tools/list and blocked if forced). Tunnel dies in 30 minutes. Add --confirm to approve every call, or --max-calls 20 for a hard budget.

peer config — claude_desktop_config.json / .cursor/mcp.json

{
  "mcpServers": {
    "teleported-docker": {
      "command": "npx",
      "args": [
        "-y",
        "mcpwire",
        "join",
        "wire://<TICKET_FROM_HOST_BANNER>"
      ]
    }
  }
}

🛡️ tool risk map — Docker

tool	risk	notes
`list_containers`	SAFE	Running container index.
`list_images`	SAFE	Image index.
`get_container_logs`	CAUTION	Logs may embed secrets — pair with --redact-secrets.
`inspect_container`	SAFE	Container details.
`run_container`	HIGH RISK	Starts arbitrary images on your daemon.
`stop_container`	HIGH RISK	Kills workloads.
`remove_container`	HIGH RISK	Deletes containers.
`prune_images`	HIGH RISK	Destructive cleanup.

🔒 Why not just share your token?

Docker's credential would grant the full toolset to a foreign LLM — including run_container and stop_container. With mcpwire the credential stays in your env; the peer only ever holds an expiring wire:// capability scoped to 3 tools.

🎥 Audit everything

Add --record session.wirelog and every call, block and redaction is logged locally. Drag the file into mcpwire.co/replay for a DevTools-style waterfall of what the remote agent actually did.

🔁 Works with every MCP client

Claude Desktop, Cursor, Windsurf, Cline — anything speaking MCP over stdio. Your peer pastes the snippet above; you keep the kill-switch (Ctrl+C) in your terminal.

What happens if the peer's agent tries to call a blocked Docker tool?

The request never reaches your MCP server. mcpwire answers with a JSON-RPC error (-32601 [MCPWire Firewall]) and logs the attempt — the tool doesn't exist from the agent's point of view, so well-behaved agents won't even try.

Can I expose the caution-level tools too?

Yes — just add them to --allow or run with --confirm so each call waits for your y/n in the host terminal. The risk map above tells you exactly what you'd be signing up for.

Is the traffic really serverless?

Yes. Discovery goes through the public Hyperswarm DHT; the data path is a direct Noise-encrypted socket between the two machines (UDP hole punching). If both NATs are stubborn, Hyperswarm routes through community relays — which only see ciphertext.

← all teleport guides ⚡ open the policy builder

🔒 MCPWire Enterprise & Team Mesh (Early Access)

Need persistent wire://your-company/db namespaces, SSO / GitHub identity verification before the P2P handshake, and centralized audit logs for compliance (SOC2 / ISO)?