prepare_reply

Get pre-populated reply data for a message: to, subject (Re:), quoted body, in_reply_to. Ready to pass to send or save_draft.

Server TrekMail MCP Server trekmail/mcp-server
Category Read
Risk class Low
Parameters 00 required

What prepare_reply does on TrekMail MCP Server

AI agents call prepare_reply to retrieve information from TrekMail MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why prepare_reply needs a policy

This tool only fetches and returns pre-formatted reply data for display or further use. It does not send a message, save a draft, or modify any data. The description explicitly states it is 'ready to pass to send or save_draft', meaning the action of sending or saving is a separate step. This is a pure read/query operation.

From the tool's definition 'Get pre-populated reply data for a message' - retrieves pre-populated fields (to, subject, quoted body, in_reply_to) without sending or saving anything

Questions about prepare_reply

What does the prepare_reply tool do? +

Get pre-populated reply data for a message: to, subject (Re:), quoted body, in_reply_to. Ready to pass to send or save_draft. It is categorised as a Read tool in the TrekMail MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on prepare_reply? +

Register the TrekMail MCP Server MCP server in PolicyLayer and add a rule for prepare_reply: 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 TrekMail MCP Server. Nothing to install.

What risk level is prepare_reply? +

prepare_reply is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit prepare_reply? +

Yes. Add a rate_limit block to the prepare_reply 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.

How do I block prepare_reply completely? +

Set action: deny in the PolicyLayer policy for prepare_reply. 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.

What MCP server provides prepare_reply? +

prepare_reply is provided by the TrekMail MCP Server MCP server (trekmail/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.