AI agents call list_funding_sources to retrieve information from Privacy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and returns existing data about linked bank accounts without creating, modifying, deleting, or executing any operations. While the data returned may be sensitive (financial account information), the tool itself performs only a read operation. Severity is low because listing funding sources does not directly enable financial transactions or data modification; it merely retrieves account metadata.
From the tool's definition Tool name is 'list_funding_sources' and description states 'Return all funding sources (bank accounts)' — this is a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Return all funding sources (bank accounts) linked to the Privacy.com account. It is categorised as a Read tool in the Privacy MCP Server, which means it retrieves data without modifying state.
Register the Privacy MCP server in PolicyLayer and add a rule for list_funding_sources: 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 Privacy. Nothing to install.
list_funding_sources 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 list_funding_sources 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 list_funding_sources. 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.
list_funding_sources is provided by the Privacy MCP server (richardadonnell/privacy-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 →