Personalize an email template for a specific prospect by injecting their data and appending a custom P.S. line. e.g., template with {{name}} and {{company}} placeholders plus prospect data returns a fully personalized email reading Hi Jane, ... at Acme Corp... plus a relevant P.S. Use for a singl...
AI agents use personalize_message to create or update resources in Sales Prospector — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sales Prospector environment.
This tool creates a personalized email message by substituting placeholders with prospect data. It produces/generates content (a Write operation) but does not send the email or commit any irreversible action. The blast radius is low since it only renders a message for review, not delivery.
From the tool's definition Personalize an email template for a specific prospect by injecting their data and appending a custom P.S. line
Attacks that exploit this kind of access
Personalize an email template for a specific prospect by injecting their data and appending a custom P.S. line. e.g., template with {{name}} and {{company}} placeholders plus prospect data returns a fully personalized email reading Hi Jane, ... at Acme Corp... plus a relevant P.S. Use for a single message; use generate_outreach_sequence for a full multi-step campaign. It is categorised as a Write tool in the Sales Prospector MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sales Prospector MCP server in PolicyLayer and add a rule for personalize_message: 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 Prospector. Nothing to install.
personalize_message 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 personalize_message 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 personalize_message. 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.
personalize_message is provided by the Sales Prospector MCP server (josephtandle/apollo-mcp-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 →