search_conversations
AI agents call search_conversations 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.
The tool searches and retrieves conversation data from LinkedIn, which is a read operation. However, severity is elevated to 'medium' rather than 'low' because: (1) the empty description creates ambiguity about exact scope, (2) conversations may contain sensitive personal/professional information, and (3) bulk retrieval via scraping could enable reconnaissance or data aggregation.
From the tool's definition Tool name 'search_conversations' indicates querying/retrieving conversation data. Server description mentions 'scraping' and 'authenticated browser automation.' The tool performs information retrieval without modifying data.
Attacks that exploit this kind of access
search_conversations. 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 search_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 MCP Server. Nothing to install.
search_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 search_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 search_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.
search_conversations is provided by the LinkedIn MCP Server MCP server (stickerdaniel/linkedin-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.