AI agents use create_invoice to create or update resources in Eyeot — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Eyeot environment.
This tool creates invoices, which are write operations that generate new financial records in an ERP system. While invoices themselves are reversible (they can be canceled or amended in most ERP systems), they are not read-only and they do commit financial obligations by documenting sales or billing transactions.
From the tool's definition Tool name is 'create_invoice' and description states 'Créer une facture' (Create an invoice). Invoices are created/recorded financial documents that modify business records.
Attacks that exploit this kind of access
Créer une facture. It is categorised as a Write tool in the Eyeot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Eyeot MCP server in PolicyLayer and add a rule for create_invoice: 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 Eyeot. Nothing to install.
create_invoice 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 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. 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 is provided by the Eyeot MCP server (https://erp.eyeot.fr/api/v1/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 →