copy_object_safe · Observability MCP: Risk & Policy

WHAT IT DOES

What copy_object_safe does on Observability

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

WHY IT NEEDS A POLICY

Why copy_object_safe needs a policy

copy_object_safe performs a reversible write operation—it duplicates data to a new location. The safeguard (failing if destination exists) prevents accidental overwriting, reducing risk compared to an unconstrained copy. However, it can still create new objects in storage, potentially consuming resources or cluttering the namespace.

From the tool's definition Tool description states it 'Copies an object to a new destination' and 'Fails if an object already exists at the destination.' This is object creation/copying functionality without overwriting existing data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

copy_object_safe Rate-limited

copy_object_safe 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": {
    "copy_object_safe": {
      "limits": [
        {
          "counter": "copy_object_safe_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 Observability, so you can run agents against it safely.

FAQ

Questions about copy_object_safe

What does the copy_object_safe tool do? +

Copies an object to a new destination. Fails if an object already exists at the destination. It is categorised as a Write tool in the Observability MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on copy_object_safe? +

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

What risk level is copy_object_safe? +

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

Can I rate-limit copy_object_safe? +

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

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

copy_object_safe is provided by the Observability MCP server (@google-cloud/observability-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.