update_draft
AI agents use update_draft to create or update resources in Gmail MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gmail MCP Server environment.
The tool modifies Gmail draft messages, which is a Write operation (creates or modifies data reversibly). Severity is high because misuse by an AI agent could result in modification of sensitive draft communications before sending, potentially altering intended messages to recipients, though the impact is confined to drafts rather than sent messages.
From the tool's definition Tool name 'update_draft' paired with sibling tools including 'create_draft', 'delete_draft', and 'batch_modify_messages' indicates data modification capability. Server description states it handles 'creating drafts' and 'managing' Gmail resources.
Attacks that exploit this kind of access
update_draft. It is categorised as a Write tool in the Gmail MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gmail MCP Server MCP server in PolicyLayer and add a rule for update_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 Gmail MCP Server. Nothing to install.
update_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_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_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_draft is provided by the Gmail MCP Server MCP server (nk900600/gmail-mcp). 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 →