report_outcome · Maiat Protocol MCP: Risk & Policy

WHAT IT DOES

What report_outcome does on Maiat Protocol

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

WHY IT NEEDS A POLICY

Why report_outcome needs a policy

This tool writes outcome/feedback data to the trust system, modifying agent reputation scores over time. It creates a new record tied to a queryId, which is a reversible write operation. While it influences trust scores (which could have downstream effects on agent economy), it doesn't directly move money, delete data, or execute code.

From the tool's definition 'Report the outcome of an interaction with an agent' and 'feeds the Maiat oracle feedback loop — making trust scores more accurate over time'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

report_outcome Rate-limited

report_outcome 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_outcome": {
      "limits": [
        {
          "counter": "report_outcome_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 Maiat Protocol, so you can run agents against it safely.

FAQ

Questions about report_outcome

What does the report_outcome tool do? +

Report the outcome of an interaction with an agent after using their service. This feeds the Maiat oracle feedback loop — making trust scores more accurate over time. Use the queryId from a previous get_agent_trust call. It is categorised as a Write tool in the Maiat Protocol 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_outcome? +

Register the Maiat Protocol MCP server in PolicyLayer and add a rule for report_outcome: 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 Maiat Protocol. Nothing to install.

What risk level is report_outcome? +

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

Can I rate-limit report_outcome? +

Yes. Add a rate_limit block to the report_outcome 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_outcome completely? +

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

report_outcome is provided by the Maiat Protocol MCP server (jhinresh/maiat-protocol). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.