Find threads that need replies by looking for specific labels
AI agents call find_unreplied_threads to retrieve information from AgentMail MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters thread data based on label criteria without altering state. It is a search/query operation with no side effects, fitting the Read category. Severity is low because even if misused, the agent only gains visibility into existing thread metadata without ability to modify or act upon messages.
From the tool's definition Tool name 'find_unreplied_threads' and description 'looking for specific labels' indicate querying/searching for threads matching criteria. No modification, deletion, execution, or financial action is performed.
Attacks that exploit this kind of access
Find threads that need replies by looking for specific labels. It is categorised as a Read tool in the AgentMail MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AgentMail MCP Server MCP server in PolicyLayer and add a rule for find_unreplied_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 AgentMail MCP Server. Nothing to install.
find_unreplied_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 find_unreplied_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 find_unreplied_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.
find_unreplied_threads is provided by the AgentMail MCP Server MCP server (kamath/agentmail-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 →