AI agents invoke build_swap to trigger actions in Agent. 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 |
|---|---|---|---|
chainId | integer | Yes | EVM chain id (mainnet = 1 in v1). |
tokenIn | string | Yes | ERC20 input token (native ETH is not supported). |
amountIn | string | Yes | Amount in base units (integer string, e.g. USDC 6dp). |
tokenOut | string | Yes | ERC20 output token. |
recipient | string | Yes | Recipient / payer address (the wallet that signs + receives). |
slippageBps | integer | — | Optional slippage budget in basis points (0–10000). |
Parameters from the server's own tool schema.
build_swap 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
Build a NON-CUSTODIAL ERC20 swap plan (approve → Permit2 sign → router.swap) for the caller to sign + broadcast. No broadcast. It is categorised as a Execute tool in the Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
build_swap accepts 6 parameters: chainId, tokenIn, amountIn, tokenOut, recipient, slippageBps. Required: chainId, tokenIn, amountIn, tokenOut, recipient. The full parameter table on this page comes from the server's own tool schema.
Register the Agent MCP server in PolicyLayer and add a rule for build_swap: 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 Agent. Nothing to install.
build_swap 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 build_swap 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 build_swap. 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.
build_swap is provided by the Agent MCP server (https://fluxiq.xyz/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
build_swap is one line of Agent's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →