AI agents call sendook_get_inbox to retrieve information from Sendook without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns information about an inbox. It performs a query operation without modifying, deleting, or executing any external operations. The blast radius of misuse is minimal—an agent could only access existing inbox details it has permission to view, with no capability to alter data or trigger external systems. Classified as Read with low severity.
From the tool's definition Tool name 'sendook_get_inbox' and description 'Get details for a specific inbox' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get details for a specific inbox. It is categorised as a Read tool in the Sendook MCP Server, which means it retrieves data without modifying state.
Register the Sendook MCP server in PolicyLayer and add a rule for sendook_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 Sendook. Nothing to install.
sendook_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 sendook_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 sendook_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.
sendook_get_inbox is provided by the Sendook MCP server (streamlinedstartup/sendook-mcp). 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 →