Medium Risk

create_purchase_order

Create a purchase order (pedido de compra) in Bling

How to control create_purchase_order ↓

What create_purchase_order does on Mcp Afip

AI agents use create_purchase_order to create or update resources in Mcp Afip — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Afip environment.

Medium Risk

Why create_purchase_order needs a policy

Creating a purchase order is a Write operation (data creation/modification) rather than Destructive (it is reversible; POs can be cancelled or modified). However, the severity is high because purchase orders are financial commitments that trigger downstream invoicing, payment obligations, and inventory effects in an accounting system.

From the tool's definition The tool description states it 'Create[s] a purchase order' — a reversible creation operation that modifies financial data in an external system (Bling). The verb 'create' indicates a Write action.

Documented attack patterns abuse exactly the kind of access create_purchase_order gives an agent:

How to control create_purchase_order

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Afip, and nothing reaches the server without passing your rules. This is the rule we recommend for create_purchase_order:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_purchase_order": {
      "limits": [
        {
          "counter": "create_purchase_order_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create_purchase_order stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Mcp Afip — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about create_purchase_order

What does the create_purchase_order tool do? +

Create a purchase order (pedido de compra) in Bling. It is categorised as a Write tool in the Mcp Afip MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_purchase_order? +

Register the Mcp Afip MCP server in PolicyLayer and add a rule for create_purchase_order: 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 Mcp Afip. Nothing to install.

What risk level is create_purchase_order? +

create_purchase_order is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_purchase_order? +

Yes. Add a rate_limit block to the create_purchase_order 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.

How do I block create_purchase_order completely? +

Set action: deny in the PolicyLayer policy for create_purchase_order. 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.

What MCP server provides create_purchase_order? +

create_purchase_order is provided by the Mcp Afip MCP server (codespar/mcp-dev-latam). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp Afip tool call.

Start from Mcp Afip, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

1300 Mcp Afip tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.