Read the full content of a Gmail draft by its draft ID.
AI agents call readGmailDraft to retrieve information from Google Workspace MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing Gmail draft content. It performs no mutations, deletions, or external operations. The only potential concern is accessing potentially sensitive email content, but classification is based on the action performed (read), not data sensitivity. This is a straightforward Read category tool with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'readGmailDraft' and description 'Read the full content of a Gmail draft by its draft ID' explicitly indicate a read-only operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
Read the full content of a Gmail draft by its draft ID. It is categorised as a Read tool in the Google Workspace MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Google Workspace MCP Server MCP server in PolicyLayer and add a rule for readGmailDraft: 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 Server. Nothing to install.
readGmailDraft is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the readGmailDraft 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 readGmailDraft. 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.
readGmailDraft is provided by the Google Workspace MCP Server MCP server (pm990320/google-workspace-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 →