Get your personalized recommended jobs from LinkedIn
AI agents call get_recommended_jobs to retrieve information from MCP-LinkedIn without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data (personalized job recommendations) from LinkedIn with no side effects, creation of new data, execution of code, deletion, or financial transactions. It is a straightforward read operation similar to fetch or list operations. The severity is low because misuse would only expose the user's own recommendation data, not system-level resources or destructive actions.
From the tool's definition The tool name 'get_recommended_jobs' and description 'Get your personalized recommended jobs from LinkedIn' indicate a retrieval operation that queries the user's LinkedIn recommendations without modifying, executing external operations, or deleting data.
Attacks that exploit this kind of access
Get your personalized recommended jobs from LinkedIn. It is categorised as a Read tool in the MCP-LinkedIn MCP Server, which means it retrieves data without modifying state.
Register the MCP-LinkedIn MCP server in PolicyLayer and add a rule for get_recommended_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 MCP-LinkedIn. Nothing to install.
get_recommended_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 get_recommended_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 get_recommended_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.
get_recommended_jobs is provided by the MCP-LinkedIn MCP server (logos-parthenos-ai/linkedin-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 →