# underwrite

Run the full underwriting: read the token, pay and verify an auditor's seal B, compose and sign seal A around it, publish the body to 0G Storage, and list it on the CollateralRegistry. Refuses with a named code at whichever step fails. Without a key this stops at the quote.

Agent View of the PolicyLayer registry record for `underwrite`. HTML page: https://policylayer.com/tools/0x402-mcp/underwrite

## Facts

- Tool: `underwrite`
- Server: 0x402 (`@0x402/mcp`) — https://policylayer.com/tools/0x402-mcp.md
- Install: `npx -y @0x402/mcp`
- Homepage: https://www.npmjs.com/package/@0x402/mcp
- Risk category: Execute (High risk)
- Registry record: grade D, identity unverified
- Server rate-limited: no
- Parameters: 5 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `token` | string | yes | ERC-20 contract address on 0G testnet. |
| `ltvBps` | integer | no | Loan-to-value to list at, in basis points. The auditor's cap always wins. |
| `settle` | boolean | no | Submit the listing transaction. False stops after the seal. |
| `source` | string | no | Local Solidity source for the token, if you have it. Never fetched. |
| `publish` | boolean | no | Upload the seal body to 0G Storage so anyone can fetch it by its hash. |

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": "underwrite",
    "arguments": {
      "token": "<token>"
    }
  }
}
```

## Why underwrite is rated High

underwrite 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 signals: Handles credentials or secrets (token)

## Use case

AI agents invoke underwrite to trigger actions in 0x402. 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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches 0x402:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "underwrite": {
      "limits": [
        {
          "counter": "underwrite_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on 0x402 (6)

- `agent_status` — Read — https://policylayer.com/tools/0x402-mcp/agent-status.md
- `describe_auditor` — Read — https://policylayer.com/tools/0x402-mcp/describe-auditor.md
- `get_listing` — Read — https://policylayer.com/tools/0x402-mcp/get-listing.md
- `hire_audit` — Read — https://policylayer.com/tools/0x402-mcp/hire-audit.md
- `quote_audit` — Read — https://policylayer.com/tools/0x402-mcp/quote-audit.md
- `verify_seal` — Read — https://policylayer.com/tools/0x402-mcp/verify-seal.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=0x402-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0x402-mcp