fleet_deploy

THE RISK

High Risk

Why fleet_deploy needs a policy

This tool executes code/commands (Docker build, systemd restart) and triggers external operations in a production environment. While not destructive per se, a misconfigured or malicious deployment could crash services, corrupt data, or compromise the production system. The blast radius is significant in a production Docker/systemd orchestration context, justifying 'high' severity.

From the tool's definition Tool description states 'Deploy an app: build and restart' — this executes build processes and systemd service restarts that trigger external operations whose effects depend on arguments (which app, which configuration).

Documented attack patterns abuse exactly the kind of access fleet_deploy gives an agent:

POLICY

How to control fleet_deploy

PolicyLayer is an MCP gateway — it sits between your AI agents and Fleet, and nothing reaches the server without passing your rules. This is the rule we recommend for fleet_deploy:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "fleet_deploy": {
      "limits": [
        {
          "counter": "fleet_deploy_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

fleet_deploy stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Fleet — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Fleet tools

Execute fleet_audit_run Run an App Store compliance audit on a mobile app project via greenlight preflight. Execute fleet_secrets_unseal Decrypt vault to /run/fleet-secrets/. WARNING: This overwrites any runtime changes that we Execute fleet_deps_scan Run a fresh dependency scan across all registered apps Execute fleet_git_push Push current branch to origin Write fleet_deps_fix Create a PR with dependency updates for an app (dry-run by default) Write fleet_audit_ignore Suppress a confirmed greenlight false positive from future audits. The finding is Write fleet_secrets_seal Seal runtime secrets back to the encrypted vault. Write fleet_deps_config Get or set dependency monitoring configuration

All 39 Fleet tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Fleet → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about fleet_deploy

What does the fleet_deploy tool do? +

Deploy an app: build and restart. It is categorised as a Execute tool in the Fleet MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on fleet_deploy? +

Register the Fleet MCP server in PolicyLayer and add a rule for fleet_deploy: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Fleet. Nothing to install.

What risk level is fleet_deploy? +

fleet_deploy is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit fleet_deploy? +

Yes. Add a rate_limit block to the fleet_deploy rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block fleet_deploy completely? +

Set action: deny in the PolicyLayer policy for fleet_deploy. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides fleet_deploy? +

fleet_deploy is provided by the Fleet MCP server (wrxck/fleet). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Fleet tool call.

Start from Fleet, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →