Retry a failed, expired, or rejected workflow execution. Creates a new workflow execution on the same account, optionally re-using the original workflow definition and customer references.
AI agents invoke retry_transaction to trigger actions in Mcp Afip. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool re-executes a workflow on an external system (AFIP electronic invoicing). In the context of Argentine tax authority invoicing, re-triggering a workflow could resubmit tax documents, invoices, or fiscal transactions. It creates new executions rather than simply reading data, and given the financial/tax context, misuse could result in duplicate invoice submissions or fiscal errors.
From the tool's definition 'Retry a failed, expired, or rejected workflow execution. Creates a new workflow execution' — triggers a new external workflow/process execution
Documented attack patterns abuse exactly the kind of access retry_transaction gives an agent:
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 retry_transaction:
{
"version": "1",
"default": "deny",
"tools": {
"retry_transaction": {
"limits": [
{
"counter": "retry_transaction_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} retry_transaction stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retry a failed, expired, or rejected workflow execution. Creates a new workflow execution on the same account, optionally re-using the original workflow definition and customer references. It is categorised as a Execute tool in the Mcp Afip MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Afip MCP server in PolicyLayer and add a rule for retry_transaction: 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.
retry_transaction is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the retry_transaction 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 retry_transaction. 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.
retry_transaction 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.
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.