AI agents call list_my_offers 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.
The tool name suggests it retrieves or lists data ('list_my') about offers, which is a read-only operation with no side effects. The empty description reduces confidence slightly, but the naming convention strongly indicates data retrieval rather than modification, deletion, or execution. Listing offers poses minimal security risk as it only exposes information already owned by the authenticated user.
From the tool's definition Tool name 'list_my_offers' indicates a retrieval operation that queries the user's existing offers without modifying them.
Attacks that exploit this kind of access
list_my_offers. 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 list_my_offers: 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.
list_my_offers 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 list_my_offers 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 list_my_offers. 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.
list_my_offers 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 →