create_invoice_draft
AI agents use create_invoice_draft to create or update resources in Mad Invoice — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mad Invoice environment.
This tool creates new invoice records in JSON storage. While creation is reversible (drafts can be deleted via delete_invoice_draft), the financial nature of invoices and potential for misuse (generating false invoices, inflating amounts) elevates severity to medium. Classified as Write rather than Financial because it operates on drafts, not committed financial transactions.
From the tool's definition Tool name 'create_invoice_draft' combined with server description stating 'creation and management of invoices' and 'Supports draft creation' indicates this tool creates new invoice data.
Attacks that exploit this kind of access
create_invoice_draft. It is categorised as a Write tool in the Mad Invoice MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mad Invoice MCP server in PolicyLayer and add a rule for create_invoice_draft: 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 Mad Invoice. Nothing to install.
create_invoice_draft 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 create_invoice_draft 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 create_invoice_draft. 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.
create_invoice_draft is provided by the Mad Invoice MCP server (mad-sol-dev/mad-invoice-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 →