List available funding accounts connected to Privacy.com
AI agents call get_funding_sources to retrieve information from ClawdPay MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about available funding sources but does not create, modify, delete, or move money. It is a simple listing/query operation. While it accesses financial account information (which could be sensitive), the action itself is read-only and has no blast radius for misuse—an agent cannot cause financial harm by merely listing funding sources. Classified as Read with low severity.
From the tool's definition Tool name 'get_funding_sources' and description 'List available funding accounts connected to Privacy.com' indicate a read-only operation that retrieves/queries data without modification or side effects.
Attacks that exploit this kind of access
List available funding accounts connected to Privacy.com. It is categorised as a Read tool in the ClawdPay MCP MCP Server, which means it retrieves data without modifying state.
Register the ClawdPay MCP server in PolicyLayer and add a rule for get_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 ClawdPay MCP. Nothing to install.
get_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 get_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 get_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.
get_funding_sources is provided by the ClawdPay MCP server (rishab87/clawdpay-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 →