Create a new Gmail draft.
AI agents use create_draft to create or update resources in Google Workspace Mcp Sidecar — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google Workspace Mcp Sidecar environment.
This tool creates new data (Gmail drafts) but does not send emails or delete content. Draft creation is reversible—drafts can be discarded or modified. The risk is medium rather than low because drafts may contain sensitive information and could be used to compose harmful communications, though actual delivery requires additional steps.
From the tool's definition Tool name 'create_draft' and description 'Create a new Gmail draft' indicate creation of new email content. The server description mentions 'email drafting' as a capability.
Attacks that exploit this kind of access
Create a new Gmail draft. It is categorised as a Write tool in the Google Workspace Mcp Sidecar MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google Workspace Mcp Sidecar MCP server in PolicyLayer and add a rule for create_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 Google Workspace Mcp Sidecar. Nothing to install.
create_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 create_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 create_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.
create_draft is provided by the Google Workspace Mcp Sidecar MCP server (milad/google-mcp-sidecar). 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 →