deploy_app · Manifest MCP: Risk & Policy

WHAT IT DOES

What deploy_app does on Manifest MCP

AI agents invoke deploy_app to trigger actions in Manifest MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why deploy_app needs a policy

This tool executes a complex multi-step operation (lease creation, domain attachment, container upload, polling) with side effects on the blockchain and external providers. While it deploys applications rather than running arbitrary code, it is fundamentally an Execute action that triggers infrastructure changes.

From the tool's definition Tool description explicitly states it "Deploy[s] a new containerized application" and "Creates a lease on-chain" and "uploads the container manifest to a provider." These are irreversible operational actions that trigger external systems and have real-world…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

deploy_app Rate-limited

deploy_app 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Manifest MCP, so you can run agents against it safely.

FAQ

Questions about deploy_app

What does the deploy_app tool do? +

Deploy a new containerized application. Requires funded credits (use fund_credit if needed). Creates a lease on-chain, optionally attaches a custom domain (FQDN) to the lease item, uploads the container manifest to a provider, and polls until ready. Use browse_catalog first to see available SKU sizes. It is categorised as a Execute tool in the Manifest MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on deploy_app? +

Register the Manifest MCP server in PolicyLayer and add a rule for deploy_app: 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 Manifest MCP. Nothing to install.

What risk level is deploy_app? +

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

Can I rate-limit deploy_app? +

Yes. Add a rate_limit block to the deploy_app 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 deploy_app completely? +

Set action: deny in the PolicyLayer policy for deploy_app. 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 deploy_app? +

deploy_app is provided by the Manifest MCP server (manifest-network/manifest-mcp-mono). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.