flash_submit_order
Execute a trade end to end: fetch a fresh quote, send any required wrap/approve transactions, sign the order with your funder wallet, and submit it. For market orders it polls until the order fills (or times out). Requires an API key and the matching funder wallet private key. This spends real fu...
This record as markdown: /tools/definitive-fi-flash-mcp/flash-submit-order.md
What flash_submit_order does on Flash
AI agents use flash_submit_order to commit financial operations through Flash, usually the final step of a payment, billing, or trading workflow. A call moves real money.
| Parameter | Type | Required | Description |
|---|---|---|---|
qty | string | Yes | Decimal amount being spent: contraAsset units for buys, targetAsset units for sells |
side | string | Yes | |
rpcUrl | string | — | Override the RPC used for on-chain wrap/approve sends |
triggers | array | — | Price triggers for stop/take-profit/bracket |
orderType | string | — | |
expireTime | string | — | ISO-8601 expiry for limit/trigger orders (omit for GTC) |
quickTrade | boolean | — | Market-only QuickTrade mode |
contraAsset | string | Yes | Address of the contra asset — spent on buys, received on sells. Native gas assets are auto-wrapped like targetAsset (the spent side is wrapped before the trade) |
contraChain | string | Yes | Chain of the contra asset (usually same as targetChain) |
maxSlippage | string | — | Slippage tolerance as a decimal, e.g. 0.01 = 1% (default 0.05) |
targetAsset | string | Yes | Address of the target (traded) asset. A native gas asset (its symbol like "ETH", "native", the zero address, or the 0xEeee… sentinel) is auto-routed through the |
targetChain | string | Yes | Chain of the target (traded) asset |
Parameters from the server's own tool schema.
Why flash_submit_order is rated Critical
This tool directly executes financial trades, spending real funds. It handles the complete transaction lifecycle including signing with a private wallet key and submitting orders. Misuse could result in unauthorized financial transactions, making it the highest severity financial risk.
From the tool's definition Execute a trade end to end... This spends real funds.
Risk signalsHigh parameter count (22 properties)
Attacks that exploit this kind of access
The rule that runs flash_submit_order safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Flash, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For flash_submit_order, this is the rule to start with:
Any call to flash_submit_order is blocked until a human approves it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Flash, apply this rule, and every flash_submit_order call is checked against it from then on.
Questions about flash_submit_order
Execute a trade end to end: fetch a fresh quote, send any required wrap/approve transactions, sign the order with your funder wallet, and submit it. For market orders it polls until the order fills (or times out). Requires an API key and the matching funder wallet private key. This spends real funds. It is categorised as a Financial tool in the Flash MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
flash_submit_order accepts 12 parameters: qty, side, rpcUrl, triggers, orderType, expireTime, quickTrade, contraAsset, contraChain, maxSlippage, targetAsset, targetChain. Required: qty, side, contraAsset, contraChain, targetAsset, targetChain. The full parameter table on this page comes from the server's own tool schema.
Register the Flash MCP server in PolicyLayer and add a rule for flash_submit_order: 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 Flash. Nothing to install.
flash_submit_order 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 flash_submit_order 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 flash_submit_order. 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.
flash_submit_order is provided by the Flash MCP server (@definitive-fi/flash-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Flash, and thousands of servers like it.
Across the catalogue