report_spam · Tru MCP: Risk & Policy

WHAT IT DOES

What report_spam does on Tru

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

PARAMETERS

Parameter	Type	Required	Description
`charge_id`	string	Yes	The charge request ID to report as spam

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why report_spam needs a policy

This tool creates or modifies data (a spam report flag on a charge record) reversibly—the flag can potentially be removed, appeals can be made, or the review can overturn the report. While it has side effects on the sender's trust level, it does not irreversibly delete the charge or financial record itself (which would be Destructive), nor does it move money (Financial).

From the tool's definition Tool description states 'flags the charge for review' and 'may affect the sender's trust level', indicating it modifies state (flagging) and impacts another entity's reputation/trust metrics without permanent deletion.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

report_spam Rate-limited

report_spam 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": {
    "report_spam": {
      "limits": [
        {
          "counter": "report_spam_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 Tru, so you can run agents against it safely.

FAQ

Questions about report_spam

What does the report_spam tool do? +

Report a charge as spam or unwanted. This flags the charge for review and may affect the sender's trust level. Requires login first. It is categorised as a Write tool in the Tru MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does report_spam accept? +

report_spam accepts 1 parameter: charge_id. Required: charge_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on report_spam? +

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

What risk level is report_spam? +

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

Can I rate-limit report_spam? +

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

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

report_spam is provided by the Tru MCP server (tru-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.