AI agents call linkedin_jobs_search to retrieve information from Linkedin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves job listings from LinkedIn without modifying, creating, deleting, or executing any actions. It is a straightforward data retrieval operation analogous to a search or list function, which falls under the Read category with low severity since misuse would only expose or retrieve publicly available job information.
From the tool's definition Tool name 'linkedin_jobs_search' and description 'Search for jobs on LinkedIn' indicate a search/query operation with no side effects.
Attacks that exploit this kind of access
Search for jobs on LinkedIn. It is categorised as a Read tool in the Linkedin MCP Server, which means it retrieves data without modifying state.
Register the Linkedin MCP server in PolicyLayer and add a rule for linkedin_jobs_search: 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. Nothing to install.
linkedin_jobs_search 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 linkedin_jobs_search 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 linkedin_jobs_search. 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.
linkedin_jobs_search is provided by the Linkedin MCP server (maheidem/linkedin-optimizer-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 →