assess_performance · AGI- MCP: Risk & Policy

WHAT IT DOES

What assess_performance does on AGI-MCP

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

WHY IT NEEDS A POLICY

Why assess_performance needs a policy

The tool records learnings, implying it writes data to persistent storage (likely the SQLite memory system described in the server). While 'assess' suggests a read/evaluation action, 'record learnings' is a write operation with side effects. It is reversible in principle (data can be overwritten or deleted), so Write is the most appropriate category rather than Destructive.

From the tool's definition Assess performance and record learnings

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

assess_performance Rate-limited

assess_performance 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": {
    "assess_performance": {
      "limits": [
        {
          "counter": "assess_performance_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 AGI-MCP, so you can run agents against it safely.

FAQ

Questions about assess_performance

What does the assess_performance tool do? +

Assess performance and record learnings. It is categorised as a Write tool in the AGI-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on assess_performance? +

Register the AGI- MCP server in PolicyLayer and add a rule for assess_performance: 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 AGI-MCP. Nothing to install.

What risk level is assess_performance? +

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

Can I rate-limit assess_performance? +

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

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

assess_performance is provided by the AGI- MCP server (muah1987/agi-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.