Exchange an authorization_code or refresh_token at POST /v1/token. Expects an already-signed JWT client_assertion. Returns access_token (5 min) + refresh_token for recurrence. Access tokens are scoped (openid, charge, refund, payment_conditions).
AI agents invoke exchange_token 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 triggers an OAuth token exchange by posting to an external endpoint, producing access tokens scoped to sensitive financial operations (charge, refund, payment_conditions). While it doesn't directly move money, it executes an external API call and returns credentials that enable financial transactions.
From the tool's definition Exchange an authorization_code or refresh_token at POST /v1/token. Returns access_token (5 min) + refresh_token for recurrence. Access tokens are scoped (openid, charge, refund, payment_conditions).
Documented attack patterns abuse exactly the kind of access exchange_token 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 exchange_token:
{
"version": "1",
"default": "deny",
"tools": {
"exchange_token": {
"limits": [
{
"counter": "exchange_token_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}exchange_token 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.
Exchange an authorization_code or refresh_token at POST /v1/token. Expects an already-signed JWT client_assertion. Returns access_token (5 min) + refresh_token for recurrence. Access tokens are scoped (openid, charge, refund, payment_conditions). 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 exchange_token: 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.
exchange_token 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 exchange_token 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 exchange_token. 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.
exchange_token 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.