multi-step-elicitation

Ask for a couple of elicitations about pizza

SERVERMcp Test Servers SOURCEmsfeldstein/mcp-test-servers

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/mcp-test-servers/multi-step-elicitation.md

WHAT IT DOES

What multi-step-elicitation does on Mcp Test Servers

AI agents call multi-step-elicitation to retrieve information from Mcp Test Servers without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why multi-step-elicitation is rated Low

This tool appears to be a simple interactive questionnaire that gathers user input about pizza preferences. It retrieves information through elicitation (asking questions) without performing any side effects, modifications to data, or external operations. This is consistent with Read category tools that passively gather information.

From the tool's definition Tool name 'multi-step-elicitation' and description 'Ask for a couple of elicitations about pizza' indicate a conversational query tool that retrieves user preferences/information through prompts.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs multi-step-elicitation safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Test Servers, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For multi-step-elicitation, this is the rule to start with:

multi-step-elicitation Allowed

multi-step-elicitation is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "multi-step-elicitation": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Test Servers, apply this rule, and every multi-step-elicitation call is checked against it from then on.

FAQ

Questions about multi-step-elicitation

What does the multi-step-elicitation tool do? +

Ask for a couple of elicitations about pizza. It is categorised as a Read tool in the Mcp Test Servers MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on multi-step-elicitation? +

Register the Mcp Test Servers MCP server in PolicyLayer and add a rule for multi-step-elicitation: 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 Mcp Test Servers. Nothing to install.

What risk level is multi-step-elicitation? +

multi-step-elicitation is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit multi-step-elicitation? +

Yes. Add a rate_limit block to the multi-step-elicitation 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 multi-step-elicitation completely? +

Set action: deny in the PolicyLayer policy for multi-step-elicitation. 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 multi-step-elicitation? +

multi-step-elicitation is provided by the Mcp Test Servers MCP server (msfeldstein/mcp-test-servers). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Mcp Test Servers, and thousands of servers like it.

This server

All 67 Mcp Test Servers tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →