AI agents use facturx_generate to create or update resources in Facturx — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Facturx environment.
This is a Write operation because it creates new structured data (XML invoice files) from input parameters. Severity is medium because while invoice documents carry financial significance, the tool itself only generates the file; actual financial commitment and submission are delegated to chorus_submit. The tool cannot directly delete, execute arbitrary commands, or move money.
From the tool's definition Tool generates (génère) a valid XML Factur-X file from billing data. The tool creates new invoice documents in standardized format (EN 16931/EU norm).
Attacks that exploit this kind of access
Génère un fichier XML Factur-X valide (norme EN 16931 / UE) à partir des données de facturation. It is categorised as a Write tool in the Facturx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Facturx MCP server in PolicyLayer and add a rule for facturx_generate: 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 Facturx. Nothing to install.
facturx_generate 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 facturx_generate 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 facturx_generate. 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.
facturx_generate is provided by the Facturx MCP server (samdreamsmaker/facturx-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 →