send_sales_email
AI agents use send_sales_email to create or update resources in Sales Agent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sales Agent environment.
The tool almost certainly sends emails via SendGrid based on the server description. Sending emails is a Write/Execute action with high blast radius — an AI agent could spam targets or send inappropriate content to real recipients. The description is empty, so confidence is reduced, but the server context strongly implies this tool triggers outbound email delivery.
From the tool's definition Tool name 'send_sales_email'; server description mentions 'sends personalized sales emails via SendGrid'
Attacks that exploit this kind of access
send_sales_email. It is categorised as a Write tool in the Sales Agent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sales Agent MCP server in PolicyLayer and add a rule for send_sales_email: 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 Sales Agent. Nothing to install.
send_sales_email 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 send_sales_email 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 send_sales_email. 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.
send_sales_email is provided by the Sales Agent MCP server (mmaun/sales-agent). 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 →