# create_reply_draft Draft a reply to an existing email, kept inside the original conversation thread. Produces an editable draft (in Drafts) that inherits the conversation, the 'RE:' subject, threading headers, and quoted history — review and send it later with send_email or via Outlook. Use this instead of create_email_draft whenever responding to a message. Agent View of the PolicyLayer registry record for `create_reply_draft`. HTML page: https://policylayer.com/tools/0xka13b-microsoft-mcps/create-reply-draft ## Facts - Tool: `create_reply_draft` - Server: Microsoft MCP (`0xka13b/microsoft-mcps`) — https://policylayer.com/tools/0xka13b-microsoft-mcps.md - Homepage: https://github.com/0xka13b/microsoft-mcps - Risk category: Write (Medium risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 4 (2 required) - Recommended policy verdict: Rate-limited ## Parameters | Parameter | Type | Required | Description | | --- | --- | --- | --- | | `cc` | array | no | Additional CC recipients to add to the reply | | `body` | string | yes | Your reply text, inserted above the quoted original message | | `email_id` | string | yes | Message ID being replied to | | `reply_all` | boolean | no | Reply to all recipients of the original (sender + to + cc) instead of just the sender. Defaults to false. | Parameters from the server's own tool schema. ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "create_reply_draft", "arguments": { "body": "", "email_id": "" } } } ``` ## Why create_reply_draft is rated Medium This tool creates a new email draft (reversible modification of user mailbox state) but does not execute the irreversible action of sending it. It falls under Write rather than Execute because drafting is a data creation operation with no external side effects until explicitly sent by the user. From the tool's own definition: "Tool description states it 'Draft[s] a reply' and produces 'an editable draft (in Drafts)' — this is reversible creation of email content." Risk signals: Accepts raw HTML/template content (body) ## Use case AI agents use create_reply_draft to create or update resources in Microsoft MCP, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Microsoft MCP environment. ## Recommended policy (PolicyLayer) Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Microsoft MCP: ```json { "version": "1", "default": "deny", "tools": { "create_reply_draft": { "limits": [ { "counter": "create_reply_draft_rate", "window": "minute", "max": 30, "scope": "grant" } ] } } } ``` ## Other tools on Microsoft MCP (13) - `delete_email` — Destructive — https://policylayer.com/tools/0xka13b-microsoft-mcps/delete-email.md - `get_attachment` — Read — https://policylayer.com/tools/0xka13b-microsoft-mcps/get-attachment.md - `get_email` — Read — https://policylayer.com/tools/0xka13b-microsoft-mcps/get-email.md - `list_emails` — Read — https://policylayer.com/tools/0xka13b-microsoft-mcps/list-emails.md - `me` — Read — https://policylayer.com/tools/0xka13b-microsoft-mcps/me.md - `search_emails` — Read — https://policylayer.com/tools/0xka13b-microsoft-mcps/search-emails.md - `unified_search` — Read — https://policylayer.com/tools/0xka13b-microsoft-mcps/unified-search.md - `create_email_draft` — Write — https://policylayer.com/tools/0xka13b-microsoft-mcps/create-email-draft.md - `move_email` — Write — https://policylayer.com/tools/0xka13b-microsoft-mcps/move-email.md - `reply_all_email` — Write — https://policylayer.com/tools/0xka13b-microsoft-mcps/reply-all-email.md - `reply_to_email` — Write — https://policylayer.com/tools/0xka13b-microsoft-mcps/reply-to-email.md - `send_email` — Write — https://policylayer.com/tools/0xka13b-microsoft-mcps/send-email.md - `update_email` — Write — https://policylayer.com/tools/0xka13b-microsoft-mcps/update-email.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=0xka13b-microsoft-mcps · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0xka13b-microsoft-mcps