List your LinkedIn connections with their name, headline, and profile URL. Optionally filter by name.
AI agents call get_connections to retrieve information from LinkedIn MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing data (connection list and metadata) without any side effects, modifications, or irreversible actions. It is purely a query/retrieval operation, placing it firmly in the Read category. The severity is low because unauthorized access to one's own connection list has limited blast radius compared to sending messages or managing connections maliciously.
From the tool's definition Tool description states 'List your LinkedIn connections' with retrieval of 'name, headline, and profile URL' with optional name filtering.
Attacks that exploit this kind of access
List your LinkedIn connections with their name, headline, and profile URL. Optionally filter by name. It is categorised as a Read tool in the LinkedIn MCP Server MCP Server, which means it retrieves data without modifying state.
Register the LinkedIn MCP Server MCP server in PolicyLayer and add a rule for get_connections: 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 MCP Server. Nothing to install.
get_connections 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_connections 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_connections. 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_connections is provided by the LinkedIn MCP Server MCP server (markswendsen-code/mcp-linkedin). 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 →