Fetch Razorpay payments for a date range. Retrieves payment details including amount, status, method, and customer info. Use this when you need to see payment transactions, check payment statuses, or get data for reconciliation. Args: from_date: Start date (YYYY-MM-DD). Defaults to yesterday. to_...
AI agents call get_payments to retrieve information from Razorpay Recon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely queries and retrieves historical payment transaction data from Razorpay for reconciliation purposes. It has no side effects, creates no new data, executes no operations, and does not commit financial actions. The read-only nature is confirmed by the description emphasizing data retrieval for auditing/reconciliation workflows.
From the tool's definition Tool description explicitly states 'Fetch Razorpay payments' and 'Retrieves payment details' with parameters limited to date range queries (from_date, to_date). Returns payment data without modification.
Attacks that exploit this kind of access
Fetch Razorpay payments for a date range. Retrieves payment details including amount, status, method, and customer info. Use this when you need to see payment transactions, check payment statuses, or get data for reconciliation. Args: from_date: Start date (YYYY-MM-DD). Defaults to yesterday. to_date: End date (YYYY-MM-DD). Defaults to today. Returns: List of payments with id, amount (in paise), status, method, and timestamps. It is categorised as a Read tool in the Razorpay Recon MCP Server, which means it retrieves data without modifying state.
Register the Razorpay Recon MCP server in PolicyLayer and add a rule for get_payments: 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 Razorpay Recon. Nothing to install.
get_payments 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_payments 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_payments. 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_payments is provided by the Razorpay Recon MCP server (qalalabs/razorpay-recon-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →