orderbook
[Requires authentication] This tool needs OAuth. If it returns an authentication error, prompt the user to connect/authenticate this MCP server (OAuth), then retry. Limit orders via the 1inch Orderbook API (v4.1). IMPORTANT: The "action" parameter is REQUIRED. Must be one of: "build", "create", "...
This record as markdown: /tools/com-1inch-business-mcp/orderbook.md
What orderbook does on 1inch MCP
AI agents use orderbook to commit financial operations through 1inch MCP, usually the final step of a payment, billing, or trading workflow. A call moves real money.
Why orderbook is rated Critical
This tool creates and manages limit orders on a DEX (1inch), which are financial commitments to swap tokens at specified prices. Creating an order commits the maker's assets to a trade. This is a financial operation with high blast radius if misused — an AI agent could create orders that transfer valuable tokens at unfavorable rates or without user intent.
From the tool's definition Limit orders via the 1inch Orderbook API (v4.1). Actions include: build, create, list, cancel — creating and managing on-chain limit orders involving token swaps.
Attacks that exploit this kind of access
The rule that runs orderbook safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 1inch MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For orderbook, this is the rule to start with:
Any call to orderbook is blocked until a human approves it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect 1inch MCP, apply this rule, and every orderbook call is checked against it from then on.
Questions about orderbook
[Requires authentication] This tool needs OAuth. If it returns an authentication error, prompt the user to connect/authenticate this MCP server (OAuth), then retry. Limit orders via the 1inch Orderbook API (v4.1). IMPORTANT: The "action" parameter is REQUIRED. Must be one of: "build", "create", "list", "cancel". Actions with example parameters: 1. build (recommended first step): { "action": "build", "chain": 1, "makerAsset": "0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48", "takerAsset": "0xdAC17F958D2ee523a2206206994597C13D831ec7", "makingAmount": "1000000", "takingAmount": "990000", "makerAddress": "0x..." } Optional: expirationSeconds (default 604800 = 7 days). With an active WalletConnect session, the order is signed and submitted automatically (set execute=false to return typed data only). 2. create (after signing typedData from build): { "action": "create", "chain": 1, "orderHash": "0x...", "signature": "0x...", "orderData": { ... } } 3. list (query orders): - By maker: { "action": "list", "chain": 1, "listMode": "by_maker", "makerAddress": "0x..." } - By hash: { "action": "list", "chain": 1, "listMode": "by_hash", "orderHash": "0x..." } - Browse: { "action": "list", "chain": 1, "listMode": "all", "limit": 10 } 4. cancel (inspect + guidance): { "action": "cancel", "chain": 1, "orderHash": "0x..." } Typical flow: build -> sign typedData -> create (or one build call when WalletConnect is connected — order signed and submitted automatically). The maker asset may require a one-time ERC-20 approval for the Limit Order Protocol; it costs native gas even though the limit order itself is gasless. When a build response includes an "approval" block, tell the user upfront (approval.estimatedCost holds the estimated cost in native units) and broadcast the included approveTx before signing. With WalletConnect, the approve is sent automatically — "approvalTxSent": true means the first wallet prompt was the one-time approval. Requires authentication. For raw HTTP access, use product_api. It is categorised as a Financial tool in the 1inch MCP MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the 1inch MCP server in PolicyLayer and add a rule for orderbook: 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 1inch MCP. Nothing to install.
orderbook 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 orderbook 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 orderbook. 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.
orderbook is provided by the 1inch MCP server (https://api.1inch.com/mcp/protocol). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 1inch, and thousands of servers like it.
Across the catalogue