AI agents call sendook_list_inboxes 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.
The 'list' verb universally indicates data retrieval with no side effects. Even without explicit description text, the consistent naming convention across the server (list_*, get_*, create_*, delete_*) establishes that 'list_inboxes' retrieves a collection of inbox records. This is a non-destructive, non-mutating query operation.
From the tool's definition Tool name 'sendook_list_inboxes' indicates a listing/retrieval operation. Description is empty, but the naming pattern aligns with sibling tools like 'sendook_list_messages' and 'sendook_list_threads', which are clearly read operations that query/enumerate…
Attacks that exploit this kind of access
sendook_list_inboxes. 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_list_inboxes: 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_list_inboxes 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_list_inboxes 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_list_inboxes. 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_list_inboxes 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 →