token_cost
LLM Token & API Cost Estimator — Estimate token count from text (or pass exact counts) and compute API cost at per-million prices.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/token-cost.md
What token_cost does on Gateway
AI agents call token_cost to retrieve information from Gateway without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | — | Text to estimate input tokens from (~4 chars/token) |
calls | integer | — | Number of identical calls to total (default 1) |
input_tokens | integer | — | Exact input token count (overrides text estimate) |
output_tokens | integer | — | Output token count |
price_per_1m_input | number | — | USD price per 1,000,000 input tokens |
price_per_1m_output | number | — | USD price per 1,000,000 output tokens (defaults to input price) |
Parameters from the server's own tool schema.
Why token_cost is rated Low
This is a pure calculation/estimation utility that takes text or numeric input and returns cost projections. It retrieves no data from external systems, modifies no state, executes no code or commands, deletes nothing, and commits no actual financial obligations. The output is informational (an estimate), not actionable financial movement.
From the tool's definition Tool 'Estimate token count from text (or pass exact counts) and compute API cost at per-million prices' performs calculation and estimation only. No modification, deletion, execution, or financial transaction occurs—it reads input and returns computed results.
Attacks that exploit this kind of access
The rule that runs token_cost safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For token_cost, this is the rule to start with:
token_cost is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every token_cost call is checked against it from then on.
Questions about token_cost
LLM Token & API Cost Estimator — Estimate token count from text (or pass exact counts) and compute API cost at per-million prices. It is categorised as a Read tool in the Gateway MCP Server, which means it retrieves data without modifying state.
token_cost accepts 6 parameters: text, calls, input_tokens, output_tokens, price_per_1m_input, price_per_1m_output. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for token_cost: 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 Gateway. Nothing to install.
token_cost 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 token_cost 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 token_cost. 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.
token_cost is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
This server
Across the catalogue