Get bills and payees set up in Chase Bill Pay.
AI agents call chase_bills to retrieve information from Chase MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads bill pay and payee information from Chase, which is a read-only operation. However, it exposes sensitive financial account data (payees, billing relationships) which raises the severity to medium. The server description confirms a read-only interface using browser automation.
From the tool's definition 'Get bills and payees set up in Chase Bill Pay' — retrieves/queries existing bill pay configuration data with no modification
Attacks that exploit this kind of access
Get bills and payees set up in Chase Bill Pay. It is categorised as a Read tool in the Chase MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Chase MCP Server MCP server in PolicyLayer and add a rule for chase_bills: 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 Chase MCP Server. Nothing to install.
chase_bills 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 chase_bills 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 chase_bills. 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.
chase_bills is provided by the Chase MCP Server MCP server (markswendsen-code/mcp-chase). 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 →