Create a short-lived access token for the Belvo Connect Widget
AI agents use create_widget_token to create or update resources in Mcp Ap2 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Ap2 environment.
This tool creates a temporary access token, which is a write operation (generating a new credential/resource). While it doesn't move money directly, tokens can grant access to financial data or operations via the Belvo Connect Widget. Given the AP2 payment protocol context, a misused token could enable unauthorized access to financial account linking flows, raising severity to medium.
From the tool's definition Create a short-lived access token for the Belvo Connect Widget
Documented attack patterns abuse exactly the kind of access create_widget_token gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for create_widget_token:
{
"version": "1",
"default": "deny",
"tools": {
"create_widget_token": {
"limits": [
{
"counter": "create_widget_token_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_widget_token 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.
Free to start. No card required.
Create a short-lived access token for the Belvo Connect Widget. It is categorised as a Write tool in the Mcp Ap2 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for create_widget_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 Ap2. Nothing to install.
create_widget_token is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_widget_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 create_widget_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.
create_widget_token is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Ap2, 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 Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.