Search transactions by keyword
AI agents call search-transactions to retrieve information from Lunchmoney without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves existing transaction records based on keyword criteria. It has no side effects—it does not create, modify, delete, or execute external operations. It is a read-only operation that simply filters and returns financial transaction data. While the data domain is financial, the action itself is retrieval only, making it a Read category tool.
From the tool's definition Tool name 'search-transactions' and description 'Search transactions by keyword' indicate a query operation that retrieves transaction data without modifying it.
Attacks that exploit this kind of access
Search transactions by keyword. It is categorised as a Read tool in the Lunchmoney MCP Server, which means it retrieves data without modifying state.
Register the Lunchmoney MCP server in PolicyLayer and add a rule for search-transactions: 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 Lunchmoney. Nothing to install.
search-transactions 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 search-transactions 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 search-transactions. 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.
search-transactions is provided by the Lunchmoney MCP server (lunchmoney-mcp-server). 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 →