AI agents call get_einvoice_archive to retrieve information from Oblio without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/downloads an existing e-Invoice archive in XML format. It performs a read-only operation that queries and returns data without creating, modifying, deleting, or executing any state changes. The blast radius is minimal—the worst outcome of misuse would be unauthorized access to invoice data, which is a confidentiality concern but not destructive or financial in nature.
From the tool's definition Tool description: 'Downloads the e-Invoice archive (XML) from Romania'. The verb 'downloads' and the action of retrieving an archive indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Downloads the e-Invoice archive (XML) from Romania. It is categorised as a Read tool in the Oblio MCP Server, which means it retrieves data without modifying state.
Register the Oblio MCP server in PolicyLayer and add a rule for get_einvoice_archive: 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 Oblio. Nothing to install.
get_einvoice_archive 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 get_einvoice_archive 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 get_einvoice_archive. 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.
get_einvoice_archive is provided by the Oblio MCP server (valentinludu/oblio-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 →