AI agents call compare_to_competitors to retrieve information from Dpx without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches and computes cost comparisons between DPX and named competitors. It performs no transactions, moves no money, and creates no obligations. It is a read-only informational/analytical tool that returns calculated savings figures based on current rates. Despite being on a financial settlement server, the tool itself only reads and compares data.
From the tool's definition 'Compare DPX settlement cost against...' and 'Returns dollar savings vs each competitor' — purely retrieves and presents comparative pricing data with no side effects
Attacks that exploit this kind of access
Compare DPX settlement cost against Stripe, Wise, JPMorgan Coin, SWIFT, PayPal, and Western Union. Returns dollar savings vs each competitor at the current DPX all-in rate. It is categorised as a Read tool in the Dpx MCP Server, which means it retrieves data without modifying state.
Register the Dpx MCP server in PolicyLayer and add a rule for compare_to_competitors: 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 Dpx. Nothing to install.
compare_to_competitors 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 compare_to_competitors 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 compare_to_competitors. 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.
compare_to_competitors is provided by the Dpx MCP server (untitledfinancial/dpx-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 →