get_inbox
AI agents call get_inbox 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 retrieves inbox content from LinkedIn, a read operation. Severity is medium rather than low because inboxes contain private messages and communications that could be sensitive if exposed to unauthorized AI agents, though the operation itself is non-destructive and non-financial.
From the tool's definition Tool named 'get_inbox' with empty description; sibling tools like 'get_feed', 'get_conversation', 'get_my_profile', and 'get_person_profile' are all read-only queries.
Attacks that exploit this kind of access
get_inbox. 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_inbox: 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_inbox 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_inbox 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_inbox. 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_inbox 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.