Low Risk

find_dispute

Fetch a dispute by id via the GraphQL node(id:) query. Returns id, status, reason, amountDisputed, receivedDate, replyByDate.

How to control find_dispute ↓

What find_dispute does on Mcp Afip

AI agents call find_dispute to retrieve information from Mcp Afip without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why find_dispute needs a policy

This tool retrieves existing dispute information for the Argentine tax authority's electronic invoicing system. It queries data without creating, modifying, deleting, or executing actions. The returned fields are informational only. Even in a financial context (AFIP tax system), the tool itself performs no financial operations—it only reads dispute metadata.

From the tool's definition Tool name 'find_dispute' and description 'Fetch a dispute by id' explicitly indicates retrieval/query operation with no modification capability. Returns read-only fields: id, status, reason, amountDisputed, receivedDate, replyByDate.

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

How to control find_dispute

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 find_dispute:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "find_dispute": {}
  }
}

find_dispute is read-only, so it stays allowed — but 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.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about find_dispute

What does the find_dispute tool do? +

Fetch a dispute by id via the GraphQL node(id:) query. Returns id, status, reason, amountDisputed, receivedDate, replyByDate. It is categorised as a Read tool in the Mcp Afip MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on find_dispute? +

Register the Mcp Afip MCP server in PolicyLayer and add a rule for find_dispute: 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 find_dispute? +

find_dispute is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit find_dispute? +

Yes. Add a rate_limit block to the find_dispute 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 find_dispute completely? +

Set action: deny in the PolicyLayer policy for find_dispute. 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 find_dispute? +

find_dispute 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.