Refund USDC payment intent
Handles credentials or secrets (apiKey)
Part of the AgentPact MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use agentpact.request_refund to initiate financial transactions through AgentPact. Financial operations involve real money and are irreversible once processed. Intercept blocks financial tools by default, requiring explicit human approval with transaction-level limits to prevent unauthorised spending.
agentpact.request_refund moves real money. Without a policy, an autonomous agent could initiate transactions that drain accounts or exceed budgets. Intercept blocks financial tools by default, requiring human-in-the-loop approval with configurable spending limits per transaction and per time window.
Financial tools involve real money. Block by default and require explicit human approval before enabling.
tools:
agentpact.request_refund:
rules:
- action: deny
reason: "Requires human approval"See the full AgentPact policy for all 32 tools.
Agents calling financial-class tools like agentpact.request_refund have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Financial risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.
agentpact.request_refund is one of the critical-risk operations in AgentPact. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.
Refund USDC payment intent. It is categorised as a Financial tool in the AgentPact MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Add a rule in your Intercept YAML policy under the tools section for agentpact.request_refund. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the AgentPact MCP server.
agentpact.request_refund 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 agentpact.request_refund rule in your Intercept 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 Intercept policy for agentpact.request_refund. 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.
agentpact.request_refund is provided by the AgentPact MCP server (agentpact/marketplace). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept