Fetch a payment by id (status, E2E id, error reason if rejected). Iniciador endpoint: GET /payments/{id}.
AI agents call get_payment to retrieve information from Mcp Ap2 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a query/fetch operation that retrieves payment information without side effects. Although the server context involves payments, this specific tool only reads payment data and does not move money, authorize transactions, or commit financial obligations. The GET endpoint pattern and the mention of fetching existing payment details confirm it is Read-category.
From the tool's definition Tool description explicitly states "Fetch a payment by id" with retrieval-only operations: "status, E2E id, error reason if rejected". HTTP method is GET, which is non-mutating. No creation, modification, deletion, or financial transaction initiation occurs.
Documented attack patterns abuse exactly the kind of access get_payment 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 get_payment:
{
"version": "1",
"default": "deny",
"tools": {
"get_payment": {}
}
}get_payment is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Fetch a payment by id (status, E2E id, error reason if rejected). Iniciador endpoint: GET /payments/{id}. It is categorised as a Read tool in the Mcp Ap2 MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for get_payment: 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.
get_payment is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_payment 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 get_payment. 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.
get_payment 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.