run_calculator
Use this when the user needs one of Calcgrid's 737 deterministic calculators and no dedicated typed tool covers it. Call it immediately after search_calculators once calculator_id and input_hints are known; do not stop at search or schema discovery. Do not use it for trivial arithmetic, live rate...
This record as markdown: /tools/com-tttkmbb-calcgrid/run-calculator.md
What run_calculator does on Calcgrid
AI agents invoke run_calculator to trigger actions in Calcgrid. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
inputs | object | Yes | Parameter names and values from search_calculators input_hints or get_calculator_schema. Use numbers as numbers, ISO dates as YYYY-MM-DD and lists as arrays. |
calculator_id | string | Yes | Exact calculator_id from search_calculators; for example 'compound-interest'. |
Parameters from the server's own tool schema.
Why run_calculator is rated High
run_calculator triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
The rule that runs run_calculator safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Calcgrid, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_calculator, this is the rule to start with:
run_calculator stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Calcgrid, apply this rule, and every run_calculator call is checked against it from then on.
Questions about run_calculator
Use this when the user needs one of Calcgrid's 737 deterministic calculators and no dedicated typed tool covers it. Call it immediately after search_calculators once calculator_id and input_hints are known; do not stop at search or schema discovery. Do not use it for trivial arithmetic, live rates or unrelated tasks. Returns typed values with units, formula, sources, freshness and timestamp; validation errors identify the field and a repair hint. It is categorised as a Execute tool in the Calcgrid MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
run_calculator accepts 2 parameters: inputs, calculator_id. Required: inputs, calculator_id. The full parameter table on this page comes from the server's own tool schema.
Register the Calcgrid MCP server in PolicyLayer and add a rule for run_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 Calcgrid. Nothing to install.
run_calculator is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_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 run_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.
run_calculator is provided by the Calcgrid MCP server (https://tttkmbb.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Calcgrid, and thousands of servers like it.
Across the catalogue