New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

send-draft

Send saved draft. Returns: sent message with id, threadId, labelIds. Use when: sending previously created draft. Note: draft is deleted after sending.

SERVERMCP Google Workspace SOURCE199-mcp/mcp-google
Medium RISK CLASS
Category Write
Parameters 00 required
Recommended Rate-limitedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/199-biotechnologies-mcp-google/send-draft.md

What send-draft does on MCP Google Workspace

AI agents use send-draft to create or update resources in MCP Google Workspace, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Google Workspace environment.

Why send-draft is rated Medium

Sending an email is a Write/communication action that delivers a message to external parties. It cannot be undone (the sent email cannot be unsent), making misuse high severity — an agent could send confidential or malicious content to unintended recipients. The draft deletion is a minor destructive side effect, but the dominant and most impactful action is the irreversible external communication.

From the tool's definition 'Send saved draft' and 'sending previously created draft' — dispatches an email to external recipients; 'draft is deleted after sending' is a side effect but the primary action is sending

Questions about send-draft

What does the send-draft tool do? +

Send saved draft. Returns: sent message with id, threadId, labelIds. Use when: sending previously created draft. Note: draft is deleted after sending. It is categorised as a Write tool in the MCP Google Workspace MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send-draft? +

Register the MCP Google Workspace MCP server in PolicyLayer and add a rule for send-draft: 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 MCP Google Workspace. Nothing to install.

What risk level is send-draft? +

send-draft is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit send-draft? +

Yes. Add a rate_limit block to the send-draft 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 send-draft completely? +

Set action: deny in the PolicyLayer policy for send-draft. 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 send-draft? +

send-draft is provided by the MCP Google Workspace MCP server (199-mcp/mcp-google). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on MCP Google Workspace, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of MCP Google Workspace's. Pull the full record:

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.