# search

Search 1inch documentation and API reference

Agent View of the PolicyLayer registry record for `search`. HTML page: https://policylayer.com/tools/com-1inch-business-mcp/search

## Facts

- Tool: `search`
- Server: 1inch MCP (`https://api.1inch.com/mcp/protocol`) — https://policylayer.com/tools/com-1inch-business-mcp.md
- Homepage: https://github.com/1inch/1inch-ai
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 4 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `page` | number | no | Page number for pagination (default 1) |
| `limit` | number | no | Maximum results per collection (default 10) |
| `query` | string | yes | Search query string |
| `include_body` | boolean | no | Include full document body in results (default true). Set to false for smaller responses. |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "search",
    "arguments": {
      "query": "<query>"
    }
  }
}
```

## Why search is rated Low

The tool retrieves and queries existing documentation and API reference materials without side effects. This is a standard read operation with minimal risk—it only returns information already publicly available. Even in the context of a financial platform (1inch is a DEX aggregator), searching documentation cannot directly move funds, execute trades, or cause irreversible changes.

From the tool's own definition: "Tool searches documentation and API reference; described as 'Search 1inch documentation' with no capability to modify, delete, or execute operations. Pure information retrieval."

## Use case

AI agents call search to retrieve information from 1inch MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches 1inch MCP:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search": {}
  }
}
```

## Other tools on 1inch MCP (8)

- `orderbook` — Financial — https://policylayer.com/tools/com-1inch-business-mcp/orderbook.md
- `product_api` — Financial — https://policylayer.com/tools/com-1inch-business-mcp/product-api.md
- `swap` — Financial — https://policylayer.com/tools/com-1inch-business-mcp/swap.md
- `walletconnect` — Financial — https://policylayer.com/tools/com-1inch-business-mcp/walletconnect.md
- `aqua` — Read — https://policylayer.com/tools/com-1inch-business-mcp/aqua.md
- `debug` — Read — https://policylayer.com/tools/com-1inch-business-mcp/debug.md
- `get_example` — Read — https://policylayer.com/tools/com-1inch-business-mcp/get-example.md
- `list_examples` — Read — https://policylayer.com/tools/com-1inch-business-mcp/list-examples.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=com-1inch-business-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-1inch-business-mcp