Preview payroll for a household employee WITHOUT creating a record. Returns the full tax breakdown (federal, state, FICA, FUTA), net pay, and employer costs. Use this to validate your request before calling run_payroll. Same parameters as run_payroll. Requires a Starter+ subscription. pay_date is...
High parameter count (13 properties)
Part of the Nannykeeper MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call preview_payroll to retrieve information from Nannykeeper without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though preview_payroll only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
preview_payroll:
rules:
- action: allowSee the full Nannykeeper policy for all 4 tools.
Agents calling read-class tools like preview_payroll have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Preview payroll for a household employee WITHOUT creating a record. Returns the full tax breakdown (federal, state, FICA, FUTA), net pay, and employer costs. Use this to validate your request before calling run_payroll. Same parameters as run_payroll. Requires a Starter+ subscription. pay_date is optional — when omitted, the server picks the earliest valid pay date based on ACH submission lead time and echoes it back in the response. v1.5.0: if pay_date is more than 5 business days in the future, the response includes is_estimated=true — those numbers will be recomputed at fire time if the user schedules. To get your employer_id and employee_id, call the NannyKeeper API: GET /api/v1/employees?employer_id=YOUR_ID (employer_id is visible in your dashboard URL).. It is categorised as a Read tool in the Nannykeeper MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for preview_payroll. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Nannykeeper MCP server.
preview_payroll 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 preview_payroll rule in your Intercept 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 Intercept policy for preview_payroll. 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.
preview_payroll is provided by the Nannykeeper MCP server (@nannykeeper/mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.