Update an existing Gmail draft by its draft ID.
AI agents use update_gmail_draft to create or update resources in Sudo Mcp Gmail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sudo Mcp Gmail environment.
This tool modifies (updates) an existing draft email reversibly—the draft can be further edited or deleted before sending. This is a Write operation, not Execute (no code/script execution) or Destructive (draft still exists and can be recovered).
From the tool's definition Tool name is 'update_gmail_draft' and description states 'Update an existing Gmail draft by its draft ID.' The verb 'update' indicates modification of existing data. The server description confirms the tool allows 'compose drafts' and manage email content.
Attacks that exploit this kind of access
Update an existing Gmail draft by its draft ID. It is categorised as a Write tool in the Sudo Mcp Gmail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sudo Mcp Gmail MCP server in PolicyLayer and add a rule for update_gmail_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 Sudo Mcp Gmail. Nothing to install.
update_gmail_draft is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_gmail_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.
Set action: deny in the PolicyLayer policy for update_gmail_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.
update_gmail_draft is provided by the Sudo Mcp Gmail MCP server (sahilyadav902/sudo-mcp-gmail). 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 →