report_result · Disvr MCP: Risk & Policy

WHAT IT DOES

What report_result does on Disvr

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

WHY IT NEEDS A POLICY

Why report_result needs a policy

This tool writes/submits feedback data to improve rankings. It creates or modifies data (ranking signals) in a reversible, non-destructive way. There are no financial, destructive, or execution implications. The blast radius is low — misuse would at most skew recommendation rankings.

From the tool's definition "Report the outcome of using a recommended tool. Helps improve future rankings."

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

report_result Rate-limited

report_result 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_result": {
      "limits": [
        {
          "counter": "report_result_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 Disvr, so you can run agents against it safely.

FAQ

Questions about report_result

What does the report_result tool do? +

Report the outcome of using a recommended tool. Helps improve future rankings. It is categorised as a Write tool in the Disvr MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on report_result? +

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

What risk level is report_result? +

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

Can I rate-limit report_result? +

Yes. Add a rate_limit block to the report_result 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_result completely? +

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

report_result is provided by the Disvr MCP server (svanik-yan/disvr). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.