mortgage_calculator
AI agents use mortgage_calculator to commit financial operations through Axiom Calculator — usually the final step of a payment, billing, or trading workflow. A call moves real money.
The tool name strongly implies financial calculations related to mortgages. Given the server context with financial sibling tools, this likely computes mortgage payment plans or amortization schedules. While it may only perform read/calculation operations rather than actually committing financial transactions, mortgage calculations can inform significant financial decisions.
From the tool's definition Tool name 'mortgage_calculator' on a server described as having 'financial calculation tools' including 'compound interest, statistics' and sibling tools like 'loan_comparison', 'rent_vs_buy', 'debt_payoff_plan'
Attacks that exploit this kind of access
mortgage_calculator. It is categorised as a Financial tool in the Axiom Calculator MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Axiom Calculator MCP server in PolicyLayer and add a rule for mortgage_calculator: 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 Axiom Calculator. Nothing to install.
mortgage_calculator is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the mortgage_calculator 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 mortgage_calculator. 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.
mortgage_calculator is provided by the Axiom Calculator MCP server (vdalhambra/axiom-calculator-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 →