AI agents call get_kwork_details 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.
This tool retrieves detailed information about a specific project/kwork using its ID as a parameter. It performs a query/fetch operation with no capability to modify, delete, or execute actions. The pattern matches other Read tools on the same server (get_dialog, get_offer, get_order_details). The blast radius of misuse is minimal—an agent could only access information already available to the user account.
From the tool's definition Tool name 'get_kwork_details' and description 'Получить подробную информацию о кворке по его ID' (Get detailed information about a kwork by its ID) indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Получить подробную информацию о кворке по его ID. 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_kwork_details: 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_kwork_details 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_kwork_details 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_kwork_details. 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_kwork_details 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 →