update_app · Manifest MCP: Risk & Policy

WHAT IT DOES

What update_app does on Manifest MCP

AI agents use update_app to create or update resources in Manifest MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Manifest MCP environment.

WHY IT NEEDS A POLICY

Why update_app needs a policy

This tool creates or modifies configuration and deployment state of running applications reversibly. While it affects live systems, the changes are non-destructive and can be reverted by issuing another update. It does not delete data or resources, nor does it execute arbitrary code directly (it updates manifests).

From the tool's definition Tool description states 'Update a deployed app with a new container manifest. Use this to change the Docker image, ports, or environment variables of a running app' — this modifies running application configuration and container deployment state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_app Rate-limited

update_app stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_app": {
      "limits": [
        {
          "counter": "update_app_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 update_app

What does the update_app tool do? +

Update a deployed app with a new container manifest. Use this to change the Docker image, ports, or environment variables of a running app without closing the lease. It is categorised as a Write tool in the Manifest MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_app? +

Register the Manifest MCP server in PolicyLayer and add a rule for update_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 update_app? +

update_app is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit update_app? +

Yes. Add a rate_limit block to the update_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 update_app completely? +

Set action: deny in the PolicyLayer policy for update_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 update_app? +

update_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.