List email drafts. Returns draft metadata including recipients and subjects.
AI agents call list_drafts to retrieve information from AgentCloak without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists draft email metadata (recipients, subjects) without side effects. It performs no modifications, deletions, or external operations. The server's design emphasizes 'read-only design' with 'PII redaction' and 'sanitization', which further supports classification as a safe Read operation.
From the tool's definition Tool name 'list_drafts' and description 'List email drafts. Returns draft metadata including recipients and subjects.' indicate a query operation that retrieves existing draft metadata without modification or deletion.
Documented attack patterns abuse exactly the kind of access list_drafts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AgentCloak, and nothing reaches the server without passing your rules. This is the rule we recommend for list_drafts:
{
"version": "1",
"default": "deny",
"tools": {
"list_drafts": {}
}
}list_drafts is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List email drafts. Returns draft metadata including recipients and subjects. It is categorised as a Read tool in the AgentCloak MCP Server, which means it retrieves data without modifying state.
Register the AgentCloak MCP server in PolicyLayer and add a rule for list_drafts: 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 AgentCloak. Nothing to install.
list_drafts 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_drafts 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_drafts. 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_drafts is provided by the AgentCloak MCP server (ryanfren/agentcloak). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AgentCloak, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 AgentCloak tools catalogued and risk-classified — across an index of 43,000+ MCP servers.