AI agents call search_jobs to retrieve information from LinkedIn Model Context Protocol (MCP) Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the tool name and context strongly suggest this retrieves job listings based on search criteria, which is a read operation with no side effects. Job searching is a standard information retrieval function. The blast radius of misuse is low—returning unwanted job results causes no harm.
From the tool's definition Tool name is 'search_jobs' and server description indicates it's for 'job searching' as a core capability. The tool operates within a job search context alongside other read-only tools like 'get_job_details', 'get_recommended_jobs', and 'list_applications'.
Documented attack patterns abuse exactly the kind of access search_jobs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LinkedIn Model Context Protocol (MCP) Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_jobs:
{
"version": "1",
"default": "deny",
"tools": {
"search_jobs": {}
}
}search_jobs is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
search_jobs. It is categorised as a Read tool in the LinkedIn Model Context Protocol (MCP) Server MCP Server, which means it retrieves data without modifying state.
Register the LinkedIn Model Context Protocol (MCP) Server MCP server in PolicyLayer and add a rule for search_jobs: 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 LinkedIn Model Context Protocol (MCP) Server. Nothing to install.
search_jobs 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 search_jobs 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 search_jobs. 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.
search_jobs is provided by the LinkedIn Model Context Protocol (MCP) Server MCP server (rayyan9477/linkedin_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from LinkedIn Model Context Protocol (MCP) Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 LinkedIn Model Context Protocol (MCP) Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.