fuel_spend
Spend a fuel tank on one menu item (fuel_menu lists them). The OWNER's turn only — an agent's own turn is refused. Draws the item's USD price in $ROKHA at the live price (half burned, half to House) and applies the effect; if the effect cannot be applied nothing is charged. Confirm the item and p...
This record as markdown: /tools/ai-rokha-rokha/fuel-spend.md
What fuel_spend does on Rokha
AI agents use fuel_spend to commit financial operations through Rokha, usually the final step of a payment, billing, or trading workflow. A call moves real money.
| Parameter | Type | Required | Description |
|---|---|---|---|
item | string | Yes | A menu item id from fuel_menu. |
target | string | — | The item's target when it needs one (scout_run: a Solana mint address). |
tank_id | string | — | Which of the caller's tanks pays (fuel_status lists them). Omit for the caller's own tank. |
wallet_address | string | — | The caller's owner identity (injected from context). |
Parameters from the server's own tool schema.
Why fuel_spend is rated Critical
Directly spends user's cryptocurrency tokens with real monetary value.
From the tool's definition Spend a fuel tank...Draws the item's USD price in $ROKHA...spends their fuel
Attacks that exploit this kind of access
The rule that runs fuel_spend safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Rokha, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fuel_spend, this is the rule to start with:
Any call to fuel_spend is blocked until a human approves it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Rokha, apply this rule, and every fuel_spend call is checked against it from then on.
Questions about fuel_spend
Spend a fuel tank on one menu item (fuel_menu lists them). The OWNER's turn only — an agent's own turn is refused. Draws the item's USD price in $ROKHA at the live price (half burned, half to House) and applies the effect; if the effect cannot be applied nothing is charged. Confirm the item and price with the owner before calling — it spends their fuel. It is categorised as a Financial tool in the Rokha MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
fuel_spend accepts 4 parameters: item, target, tank_id, wallet_address. Required: item. The full parameter table on this page comes from the server's own tool schema.
Register the Rokha MCP server in PolicyLayer and add a rule for fuel_spend: 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 Rokha. Nothing to install.
fuel_spend 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 fuel_spend 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 fuel_spend. 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.
fuel_spend is provided by the Rokha MCP server (https://rokha.ai/mcp/jsonrpc). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Rokha, and thousands of servers like it.
Across the catalogue