AI agents call spending_summary_tool to retrieve information from Plaid without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and aggregates existing transaction data into summary reports. It performs no mutations, deletions, or financial transactions. Even though it accesses financial data, the action itself is purely analytical retrieval. The read-only nature of the server and the tool's aggregation-only function confirm it belongs in the Read category with low severity.
From the tool's definition Tool name is 'spending_summary_tool' and description states 'Aggregate spending by category | subcategory | merchant | account.' This is a data retrieval and aggregation operation with no modification, deletion, or external action.
Attacks that exploit this kind of access
Aggregate spending by category | subcategory | merchant | account. It is categorised as a Read tool in the Plaid MCP Server, which means it retrieves data without modifying state.
Register the Plaid MCP server in PolicyLayer and add a rule for spending_summary_tool: 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 Plaid. Nothing to install.
spending_summary_tool 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 spending_summary_tool 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 spending_summary_tool. 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.
spending_summary_tool is provided by the Plaid MCP server (t-rhex/plaid-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 →