AI agents call linkedin_people_get_profile 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 profile data from LinkedIn without side effects. However, severity is medium rather than low because profile information can be personally identifiable data (PII) that could be sensitive if accessed without proper consent or used maliciously in bulk retrieval scenarios. The tool itself is Read-category, but the data it exposes warrants caution.
From the tool's definition Tool name contains 'get' and description states 'Get member profile information', indicating retrieval without modification.
Attacks that exploit this kind of access
Get member profile information. 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_people_get_profile: 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_people_get_profile 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_people_get_profile 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_people_get_profile. 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_people_get_profile 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 →