Query transaction status
AI agents call query_transaction to retrieve information from PayFast MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries transaction status, which is a data retrieval operation. It does not create, modify, delete, or execute transactions; it only inspects their state. While the broader PayFast server handles financial operations, this specific tool is narrowly scoped to read-only status checks.
From the tool's definition Tool name is 'query_transaction' and description states 'Query transaction status' — a read-only operation that retrieves existing data without modification or side effects.
Attacks that exploit this kind of access
Query transaction status. It is categorised as a Read tool in the PayFast MCP MCP Server, which means it retrieves data without modifying state.
Register the PayFast MCP server in PolicyLayer and add a rule for query_transaction: 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 PayFast MCP. Nothing to install.
query_transaction 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 query_transaction 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 query_transaction. 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.
query_transaction is provided by the PayFast MCP server (theyahia/payfast-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 →