A tool that collects user information through elicitation
AI agents call collect-user-info to retrieve information from Codemesh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool gathers or retrieves user information rather than creating, modifying, deleting, or executing code. 'Elicitation' suggests interactive questioning to obtain data. This is a Read operation. Severity is low because information collection itself has minimal blast radius unless the collected data is later misused by downstream tools, but that is outside this tool's scope.
From the tool's definition Tool name 'collect-user-info' and description 'collects user information through elicitation' indicate data retrieval/gathering without modification, deletion, or execution of external operations.
Documented attack patterns abuse exactly the kind of access collect-user-info gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Codemesh, and nothing reaches the server without passing your rules. This is the rule we recommend for collect-user-info:
{
"version": "1",
"default": "deny",
"tools": {
"collect-user-info": {}
}
}collect-user-info is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
A tool that collects user information through elicitation. It is categorised as a Read tool in the Codemesh MCP Server, which means it retrieves data without modifying state.
Register the Codemesh MCP server in PolicyLayer and add a rule for collect-user-info: 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 Codemesh. Nothing to install.
collect-user-info is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the collect-user-info 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.
Set action: deny in the PolicyLayer policy for collect-user-info. 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.
collect-user-info is provided by the Codemesh MCP server (kiliman/codemesh). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Codemesh, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 Codemesh tools catalogued and risk-classified — across an index of 43,000+ MCP servers.