Given one or more transaction IDs, fetch their related/linked transactions. Pass IDs as an array of strings.
AI agents call get_related_transactions to retrieve information from Money Lover MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and queries financial transaction data without altering, deleting, or executing actions. It falls squarely into the Read category as it only retrieves information.
From the tool's definition Tool description states it 'fetch[es]' related transactions given transaction IDs—a query operation with no modification or side effects.
Attacks that exploit this kind of access
Given one or more transaction IDs, fetch their related/linked transactions. Pass IDs as an array of strings. It is categorised as a Read tool in the Money Lover MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Money Lover MCP Server MCP server in PolicyLayer and add a rule for get_related_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 Money Lover MCP Server. Nothing to install.
get_related_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 get_related_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 get_related_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.
get_related_transactions is provided by the Money Lover MCP Server MCP server (juansebashr/moneylover-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 →