AI agents call get_user_info to retrieve information from Kwork without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description lowering confidence slightly, the 'get_' prefix and analogous sibling tools on a marketplace platform (Kwork) strongly indicate this is a read-only query that retrieves user information with no side effects. User info queries are typically low-blast operations unless they expose highly sensitive authentication tokens, which is unlikely for a standard user profile getter.
From the tool's definition Tool name 'get_user_info' indicates a retrieval operation. The empty description and context of sibling tools (get_dialog, get_kwork_details, get_me) suggest this fetches user profile data without modification.
Attacks that exploit this kind of access
get_user_info. It is categorised as a Read tool in the Kwork MCP Server, which means it retrieves data without modifying state.
Register the Kwork MCP server in PolicyLayer and add a rule for get_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 Kwork. Nothing to install.
get_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 get_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 get_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.
get_user_info is provided by the Kwork MCP server (simonether/kwork-mcp). 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 →