发送Gmail邮件
AI agents use gmailSend to create or update resources in Remote MCP Server on Cloudflare — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Remote MCP Server on Cloudflare environment.
Sending emails is a Write operation—it creates new data (email messages) with reversible effects (emails can be unsent within short windows or deleted). However, it carries high severity because an AI agent with this capability could send emails on behalf of the user to arbitrary recipients with arbitrary content, potentially impersonating the user, phishing others, or causing reputational harm.
From the tool's definition Tool name is 'gmailSend' and description states '发送Gmail邮件' (send Gmail email in Chinese). This directly indicates the tool sends/creates email messages.
Attacks that exploit this kind of access
发送Gmail邮件. It is categorised as a Write tool in the Remote MCP Server on Cloudflare MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Remote MCP Server on Cloudflare MCP server in PolicyLayer and add a rule for gmailSend: 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 Remote MCP Server on Cloudflare. Nothing to install.
gmailSend 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 gmailSend 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 gmailSend. 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.
gmailSend is provided by the Remote MCP Server on Cloudflare MCP server (williamsuiself/remote-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 →