Capture a pre-authorized order (pre_authorized → paid)
AI agents use capture_charge to commit financial operations through Mcp Ap2 — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool moves money by finalizing a payment charge. The transition from pre-authorized to paid status represents an irreversible commitment of funds. In the context of a payment protocol server, capture operations are standard financial controls but present critical risk if invoked by a compromised or adversarial agent, as they directly debit accounts without additional authorization checks.
From the tool's definition Tool name 'capture_charge' in AP2 (Google's Agent-to-Agent Payment Protocol); description states 'Capture a pre-authorized order (pre_authorized → paid)' — explicitly transitions pre-authorized payment to charged/paid state, committing financial obligation.
Documented attack patterns abuse exactly the kind of access capture_charge 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 capture_charge:
{
"version": "1",
"default": "deny",
"tools": {
"capture_charge": {
"deny_if": [
{
"conditions": [],
"on_deny": "Requires human approval."
}
]
}
}
}Any call to capture_charge is blocked until a human approves it. The rest of the server keeps working.
Free to start. No card required.
Capture a pre-authorized order (pre_authorized → paid). It is categorised as a Financial tool in the Mcp Ap2 MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for capture_charge: 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.
capture_charge is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the capture_charge 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 capture_charge. 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.
capture_charge 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.