AI agents call get_conversations to retrieve information from LinkedIn Intelligence MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves messaging/conversation data from LinkedIn. While classified as Read (no side effects), severity is elevated to medium due to the sensitive personal nature of private messages and conversations, which could expose private communications if accessed inappropriately by an AI agent.
From the tool's definition Tool name 'get_conversations' with no description provided. Based on naming convention and server context (messaging capability mentioned in server description), this retrieves conversation data. The verb 'get' indicates a read operation without modification.
Documented attack patterns abuse exactly the kind of access get_conversations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LinkedIn Intelligence MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_conversations:
{
"version": "1",
"default": "deny",
"tools": {
"get_conversations": {}
}
}get_conversations 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.
get_conversations. It is categorised as a Read tool in the LinkedIn Intelligence MCP Server MCP Server, which means it retrieves data without modifying state.
Register the LinkedIn Intelligence MCP Server MCP server in PolicyLayer and add a rule for get_conversations: 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 Intelligence MCP Server. Nothing to install.
get_conversations 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_conversations 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_conversations. 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_conversations is provided by the LinkedIn Intelligence MCP Server MCP server (southleft/linkedin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 87 LinkedIn Intelligence MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
87 LinkedIn Intelligence MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.