# l402-fetch

Fetch a URL with automatic payment handling (L402 Lightning + x402 on-chain). Manages credentials, pays automatically when autoPay is true and cost is within budget, and retries. For human wallets, returns a payment page URL or QR code. For x402 services, returns payment details (receiver address, network, asset, amount) — the user pays in their wallet and provides the transaction hash. Set autoPay to true for seamless access. When a 402 is returned with tiers, present the pricing options to the user and use l402-buy-credits to purchase their chosen tier. For widget hosts, call l402-fetch-preview first to show a payment confirmation dialog before spending.

Agent View of the PolicyLayer registry record for `l402-fetch`. HTML page: https://policylayer.com/tools/dev-forgesworn-402-mcp/l402-fetch

## Facts

- Tool: `l402-fetch`
- Server: 402 (`402-mcp`) — https://policylayer.com/tools/dev-forgesworn-402-mcp.md
- Install: `npx -y 402-mcp`
- Homepage: https://github.com/forgesworn/402-mcp
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "l402-fetch",
    "arguments": {}
  }
}
```

## Why l402-fetch is rated Low

Even though l402-fetch only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

## Use case

AI agents call l402-fetch to retrieve information from 402 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 402:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "l402-fetch": {}
  }
}
```

## Other tools on 402 (9)

- `l402-buy-credits` — Financial — https://policylayer.com/tools/dev-forgesworn-402-mcp/l402-buy-credits.md
- `l402-pay` — Financial — https://policylayer.com/tools/dev-forgesworn-402-mcp/l402-pay.md
- `l402-redeem-cashu` — Financial — https://policylayer.com/tools/dev-forgesworn-402-mcp/l402-redeem-cashu.md
- `l402-balance` — Read — https://policylayer.com/tools/dev-forgesworn-402-mcp/l402-balance.md
- `l402-config` — Read — https://policylayer.com/tools/dev-forgesworn-402-mcp/l402-config.md
- `l402-credentials` — Read — https://policylayer.com/tools/dev-forgesworn-402-mcp/l402-credentials.md
- `l402-discover` — Read — https://policylayer.com/tools/dev-forgesworn-402-mcp/l402-discover.md
- `l402-search` — Read — https://policylayer.com/tools/dev-forgesworn-402-mcp/l402-search.md
- `l402-store-token` — Write — https://policylayer.com/tools/dev-forgesworn-402-mcp/l402-store-token.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=dev-forgesworn-402-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/dev-forgesworn-402-mcp