aqua

SERVER1inch MCP SOURCEhttps://api.1inch.com/mcp/protocol

High RISK CLASS

Category Execute

Parameters 126 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/com-1inch-business-mcp/aqua.md

WHAT IT DOES

What aqua does on 1inch MCP

AI agents invoke aqua to trigger actions in 1inch MCP. 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
`app`	string	—	App / AquaSwapVMRouter address (strategy_* reads, close_position).
`sort`	string	—	Sort direction for list/activity/volume (asc\|desc).
`limit`	integer	Yes	Page size for list/activity/volume actions.
`maker`	string	—	Maker EVM address (strategy_* reads, create_position).
`action`	string	Yes	Invalid or missing "action" parameter. Must be one of: "maker_stats", "list_maker_strategies", "strategy_overview", "strategy_activity", "strategy_volume", "lis
`cursor`	string	—	Opaque pagination cursor from a previous response.
`status`	array	Yes	Filter by lifecycle status for list_maker_strategies (e.g. ["open"]).
`tokens`	object	Yes	create_position: exactly two legs [{ token, amount }, { token, amount }] (amount in smallest units, as a string). close_position: array of token addresses to wi
`address`	string	—	Maker EVM address (maker_stats, list_maker_strategies).
`chainId`	object	Yes	EVM chain ID (number) for single-strategy / write actions, or an array of chain IDs for list/stats filters.
`execute`	boolean	—	Optional. When a WalletConnect session is active, defaults to true: the transaction is sent via the wallet (user confirms the prompt). Authenticated sessions ma
`feeBpsIn`	integer	Yes	Optional taker fee in basis points for create_position (1-500).

Parameters from the server's own tool schema.

RISK

Why aqua is rated High

aqua 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.

Risk signalsHigh parameter count (22 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs aqua 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 aqua, this is the rule to start with:

aqua Rate-limited

aqua stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "aqua": {
      "limits": [
        {
          "counter": "aqua_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect 1inch MCP, apply this rule, and every aqua call is checked against it from then on.

FAQ

Questions about aqua

What does the aqua tool do? +

1inch Aqua (shared-liquidity market making): position analytics plus maker position writes. Write actions (OAuth, or WalletConnect + signed 1inch ToS (pass walletSessionToken after MCP session rotation); non-custodial — the user's wallet signs): create_position (two-phase: call once for a preview + previewRef, then again with confirmed:true), close_position (confirmed:true; closing is permanent). Anonymous writes execute only via WalletConnect (execute=false is rejected). REQUIRED: "action" — read actions (no OAuth): maker_stats, list_maker_strategies, strategy_overview, strategy_activity, strategy_volume, list_opened. Read the resource file://1inch-mcp/guides/aqua-workflow for per-action examples, priceRange semantics, and maker position flows. Raw HTTP: product_api with path "/aqua/v1.0/strategies/...". It is categorised as a Execute tool in the 1inch MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does aqua accept? +

aqua accepts 12 parameters: app, sort, limit, maker, action, cursor, status, tokens, address, chainId, execute, feeBpsIn. Required: limit, action, status, tokens, chainId, feeBpsIn. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on aqua? +

Register the 1inch MCP server in PolicyLayer and add a rule for aqua: 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.

What risk level is aqua? +

aqua is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit aqua? +

Yes. Add a rate_limit block to the aqua 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.

How do I block aqua completely? +

Set action: deny in the PolicyLayer policy for aqua. 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.

What MCP server provides aqua? +

aqua 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.

KEEP EXPLORING

More on 1inch, and thousands of servers like it.

This server

All 10 1inch tools → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →