AI agents call get_income_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 retrieves income information from bank accounts—a Read operation with no side effects. However, severity is high because income data is sensitive personal financial information that could be exploited if exposed to a malicious agent; disclosure of income streams could enable social engineering, targeting, or inference of financial status.
From the tool's definition Tool name 'get_income_tool' and description 'Bank-detected income streams' indicate data retrieval with no modification capability. Server explicitly described as 'read-only MCP server'.
Attacks that exploit this kind of access
Bank-detected income streams. Requires Income product enabled in your Plaid dashboard. 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 get_income_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.
get_income_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 get_income_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 get_income_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.
get_income_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 →