List conversation threads for an inbox.
AI agents call list_threads to retrieve information from Lobstermail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing conversation thread metadata from an inbox without modifying, deleting, or executing any operations. It is a straightforward data retrieval function with no destructive or executable side effects. The blast radius of misuse is minimal—an agent could only enumerate threads to which it already has access.
From the tool's definition Tool name 'list_threads' and description 'List conversation threads for an inbox' indicate a retrieval operation with no side effects. The verb 'list' is a classic read operation.
Attacks that exploit this kind of access
List conversation threads for an inbox. It is categorised as a Read tool in the Lobstermail MCP Server, which means it retrieves data without modifying state.
Register the Lobstermail MCP server in PolicyLayer and add a rule for list_threads: 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 Lobstermail. Nothing to install.
list_threads 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 list_threads 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 list_threads. 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.
list_threads is provided by the Lobstermail MCP server (lobster-kit/mcp-server-lobstermail). 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 →