Query billing/financial data in OfficeRnD. action=list: List entities with optional filters and pagination (max 50 per page). action=get: Get a single entity by ID (payments, plans). action=coin_stats: Get coin/credit balance for a member or company in a given month. Entity-specific filters when ...
AI agents call billing to retrieve information from OfficeRnD MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although the tool accesses financial data (payments, plans, billing records), it only retrieves and queries this information with no ability to modify, charge, refund, or move money. The read-only constraint and query-only actions (list, get, coin_stats) place this squarely in the Read category.
From the tool's definition Tool description states 'read-only MCP server' and all actions are query-based: 'list' (list entities with filters), 'get' (get single entity by ID), and 'coin_stats' (get balance). No write, delete, or financial transaction capabilities are present.
Attacks that exploit this kind of access
Query billing/financial data in OfficeRnD. action=list: List entities with optional filters and pagination (max 50 per page). action=get: Get a single entity by ID (payments, plans). action=coin_stats: Get coin/credit balance for a member or company in a given month. Entity-specific filters when listing: - payments: status, member, company, documentType (creditNote|invoice|overpayment|paymentCharge), dateFrom, dateTo (ISO dates), sort (e.g. It is categorised as a Read tool in the OfficeRnD MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OfficeRnD MCP Server MCP server in PolicyLayer and add a rule for billing: 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 OfficeRnD MCP Server. Nothing to install.
billing 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 billing 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 billing. 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.
billing is provided by the OfficeRnD MCP Server MCP server (mrboor/officernd-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 →