CRM pipeline: leads by status, hot leads, contacts, opportunities, total pipeline value.
AI agents call maasy_get_crm_summary to retrieve information from Maasy — AI Marketing Copilot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves CRM pipeline information without creating, modifying, or deleting records. It is a Read operation. Severity is medium because exposure of CRM pipeline data (lead status, opportunity values, contact details) could enable competitive intelligence theft, lead poaching, or social engineering if an untrusted agent gains access.
From the tool's definition Tool retrieves CRM data: 'leads by status, hot leads, contacts, opportunities, total pipeline value' — all queries with no modification or deletion.
Attacks that exploit this kind of access
CRM pipeline: leads by status, hot leads, contacts, opportunities, total pipeline value. It is categorised as a Read tool in the Maasy — AI Marketing Copilot MCP Server, which means it retrieves data without modifying state.
Register the Maasy — AI Marketing Copilot MCP server in PolicyLayer and add a rule for maasy_get_crm_summary: 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 Maasy — AI Marketing Copilot. Nothing to install.
maasy_get_crm_summary 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 maasy_get_crm_summary 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 maasy_get_crm_summary. 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.
maasy_get_crm_summary is provided by the Maasy — AI Marketing Copilot MCP server (@maasy-ai/mcp-server). 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 →