AI agents call list_job_posts to retrieve information from Kula Ai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays existing job post data from the job board without creating, modifying, deleting, or executing any operations. It is a straightforward query operation that has no impact on system state. The low severity reflects minimal blast radius—misuse would only expose publicly available job board information.
From the tool's definition Tool name is 'list_job_posts' and description states 'List published job posts on the job board.' The verb 'list' and the action of retrieving/querying published job posts indicates a read-only operation with no side effects.
Attacks that exploit this kind of access
List published job posts on the job board. Only use when the user explicitly asks about job board listings. It is categorised as a Read tool in the Kula Ai MCP Server, which means it retrieves data without modifying state.
Register the Kula Ai MCP server in PolicyLayer and add a rule for list_job_posts: 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 Kula Ai. Nothing to install.
list_job_posts 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_job_posts 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_job_posts. 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_job_posts is provided by the Kula Ai MCP server (kula-ai/kula-mcp-server). 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 →