Get recent transaction history for a bank account.
AI agents call get_transaction_history to retrieve information from MCP Banking Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read category tool as it retrieves historical data without modifying, deleting, or executing operations. Severity is medium rather than low because transaction history can be sensitive financial information that, if exposed to an unauthorized agent, could leak account details, balance patterns, or transaction metadata.
From the tool's definition Tool name is 'get_transaction_history' and description states it 'Get[s] recent transaction history for a bank account' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get recent transaction history for a bank account. It is categorised as a Read tool in the MCP Banking Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Banking Server MCP server in PolicyLayer and add a rule for get_transaction_history: 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 Banking Server. Nothing to install.
get_transaction_history 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_transaction_history 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_transaction_history. 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_transaction_history is provided by the MCP Banking Server MCP server (sksingh2005/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 →