search_users
AI agents call search_users to retrieve information from Dynamic Per-User Tool Generation MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'search_' prefix is a standard convention for retrieval operations that do not modify state. Without a description, we rely on the name and context. The tool appears designed to query user information from the system, which is a typical read operation. No evidence suggests data modification, deletion, execution of arbitrary code, or financial impact.
From the tool's definition Tool named 'search_users' with empty description; naming convention ('search_') strongly indicates a read-only query operation. Sibling tools (search_entities_by_type, echo, add, multiply) are read/compute operations, consistent with a Read classification.
Attacks that exploit this kind of access
search_users. It is categorised as a Read tool in the Dynamic Per-User Tool Generation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Dynamic Per-User Tool Generation MCP Server MCP server in PolicyLayer and add a rule for search_users: 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 Dynamic Per-User Tool Generation MCP Server. Nothing to install.
search_users 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 search_users 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 search_users. 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.
search_users is provided by the Dynamic Per-User Tool Generation MCP Server MCP server (shivampansuriya/mcp-server-python). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →