update_object_metadata · Observability MCP: Risk & Policy

WHAT IT DOES

What update_object_metadata does on Observability

AI agents use update_object_metadata 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 update_object_metadata needs a policy

This tool creates or modifies data in a reversible manner, fitting the Write category. Severity is medium because unauthorized metadata updates could affect object visibility, permissions, or attributes in GCP storage, but the impact is typically limited and can be corrected.

From the tool's definition Tool name 'update_object_metadata' and description 'Updates the metadata of an existing object' indicate modification of existing data. The action is reversible (metadata can be updated again) and does not involve deletion or destructive operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_object_metadata Rate-limited

update_object_metadata 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_object_metadata": {
      "limits": [
        {
          "counter": "update_object_metadata_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 update_object_metadata

What does the update_object_metadata tool do? +

Updates the metadata of an existing object. 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 update_object_metadata? +

Register the Observability MCP server in PolicyLayer and add a rule for update_object_metadata: 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 update_object_metadata? +

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

Can I rate-limit update_object_metadata? +

Yes. Add a rate_limit block to the update_object_metadata 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_object_metadata completely? +

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

update_object_metadata 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.