AI agents use send_inmail to create or update resources in Unipile — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Unipile environment.
An AI agent can call send_inmail faster than any human can review — one bad instruction and it creates or modifies resources in Unipile by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Send InMail to non-connections (requires LinkedIn Premium/Sales Nav). It is categorised as a Write tool in the Unipile MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Unipile MCP server in PolicyLayer and add a rule for send_inmail: 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 Unipile. Nothing to install.
send_inmail is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the send_inmail 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 send_inmail. 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.
send_inmail is provided by the Unipile MCP server (sundeepg98/mcp-server-unipile). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.