job_finder
AI agents call job_finder to retrieve information from MCP Starter for Puch AI without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Job search and opportunity discovery are inherently read-only operations that retrieve or query existing job data without modifying or deleting records. The tool fits the 'Read' category as it searches and retrieves job postings. Severity is low because misuse would at worst return irrelevant job results with minimal blast radius.
From the tool's definition Tool name 'job_finder' and server description stating 'job search capabilities including analyzing job descriptions, fetching job postings from URLs, and searching opportunities' indicate data retrieval operations.
Attacks that exploit this kind of access
job_finder. It is categorised as a Read tool in the MCP Starter for Puch AI MCP Server, which means it retrieves data without modifying state.
Register the MCP Starter for Puch AI MCP server in PolicyLayer and add a rule for job_finder: 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 MCP Starter for Puch AI. Nothing to install.
job_finder 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 job_finder 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 job_finder. 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.
job_finder is provided by the MCP Starter for Puch AI MCP server (kulraj69/mcp-llm). 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 →