Get detailed cost, revenue, margin, and recent events for a single customer
AI agents call margint_get_customer to retrieve information from Margint Ai 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 financial and operational metrics for a customer account. While the data retrieved is sensitive (costs, margins, revenue), the tool itself performs no writes, modifications, deletions, or financial transactions. It is purely informational. The blast radius of accidental misuse is limited to information disclosure rather than unauthorized changes or fund movements.
From the tool's definition Tool retrieves 'detailed cost, revenue, margin, and recent events for a single customer' — a read-only query operation with no modification, deletion, or financial transaction capabilities.
Attacks that exploit this kind of access
Get detailed cost, revenue, margin, and recent events for a single customer. It is categorised as a Read tool in the Margint Ai MCP Server, which means it retrieves data without modifying state.
Register the Margint Ai MCP server in PolicyLayer and add a rule for margint_get_customer: 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 Margint Ai. Nothing to install.
margint_get_customer 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 margint_get_customer 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 margint_get_customer. 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.
margint_get_customer is provided by the Margint Ai MCP server (margint-ai/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 →