startElicitation · My MCP: Risk & Policy

WHAT IT DOES

What startElicitation does on My

AI agents invoke startElicitation to trigger actions in My. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why startElicitation needs a policy

Without a description, the name alone suggests this tool triggers or executes some elicitation process (likely data collection, user interaction, or external workflow). The 'start' verb indicates it initiates an operation whose side effects are not fully specified. Given the ambiguity and the potential for an agent to trigger uncontrolled external operations, Execute is the appropriate category.

From the tool's definition Tool name 'startElicitation' suggests initiation of an external operation or process. The suffix 'start' indicates triggering an action whose effects depend on runtime behavior. No description provided to clarify scope.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

startElicitation Rate-limited

startElicitation stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "startElicitation": {
      "limits": [
        {
          "counter": "startelicitation_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches My, so you can run agents against it safely.

FAQ

Questions about startElicitation

What does the startElicitation tool do? +

startElicitation. It is categorised as a Execute tool in the My MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on startElicitation? +

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

What risk level is startElicitation? +

startElicitation is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit startElicitation? +

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

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

startElicitation is provided by the My MCP server (kcbabo/everything-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.