upload_object_safe · Observability MCP: Risk & Policy

WHAT IT DOES

What upload_object_safe does on Observability

AI agents use upload_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 upload_object_safe needs a policy

Uploading files to cloud storage is a write operation that creates new data. While it modifies the GCS bucket's contents, the safety mechanism (failing if object exists) prevents accidental overwrites and makes this reversible (files can be deleted).

From the tool's definition Tool description states 'Uploads a file to a GCS bucket' which is a create/modify data operation. The 'safe' variant prevents overwriting existing objects, limiting destructive potential.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

upload_object_safe Rate-limited

upload_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": {
    "upload_object_safe": {
      "limits": [
        {
          "counter": "upload_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 upload_object_safe

What does the upload_object_safe tool do? +

Uploads a file to a GCS bucket. Fails if the object already exists. 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 upload_object_safe? +

Register the Observability MCP server in PolicyLayer and add a rule for upload_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 upload_object_safe? +

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

Can I rate-limit upload_object_safe? +

Yes. Add a rate_limit block to the upload_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 upload_object_safe completely? +

Set action: deny in the PolicyLayer policy for upload_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 upload_object_safe? +

upload_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.