# foura_auto

Give a URL, get the content back. The default first choice for any page when you just want the data and don't want to decide how to fetch it. Internally it walks a cost-aware ladder - a fast direct request first, then a rotating proxy, then a full browser session - escalating only as far as the target forces it, solving common bot challenges (Cloudflare, and similar) on the way, and cheaply replaying a warm session on repeat calls to the same host. It learns the right settings per host on its own, so there are no maxTries / pool / retry knobs to tune. Pass validate (a substring the real page must contain) on protected targets so it can tell a real page from a challenge page. The response includes a meta trace (which rung delivered, credits spent) and, by default, the winning session ({proxy, cookies, userAgent}) so you can replay it through foura_single / foura_proxy afterwards. Use one of the lower-level tools instead only when you need explicit control: foura_single for a specific raw HTTP request, foura_proxy to drive the rotation/exit yourself, foura_browser for a scripted browser session.

Agent View of the PolicyLayer registry record for `foura_auto`. HTML page: https://policylayer.com/tools/ai-foura-mcp/foura-auto

## Facts

- Tool: `foura_auto`
- Server: Mcp (`@fouradata/mcp`) — https://policylayer.com/tools/ai-foura-mcp.md
- Install: `npx -y @fouradata/mcp`
- Homepage: https://github.com/fouradata/mcp
- Risk category: Read (Low risk)
- Registry record: grade D, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 11 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `url` | string | yes | Target URL. Public hosts only - private/reserved ranges (RFC 1918 10/8, 172.16/12, 192.168/16, loopback 127/8, link-local, IPv6 ULA fc00::/7, IPv6 loopback ::1, |
| `data` | object | no | Request body for non-GET methods. Strings sent as-is; objects auto-serialized to JSON. |
| `method` | string | no | HTTP method for the target request (default GET). |
| `headers` | array | no | Custom HTTP headers to send to the TARGET, as [name, value] tuples. Example: [["Accept", "application/json"], ["Authorization", "Bearer ..."]] |
| `validate` | object | no | Post-fetch response validation. When the response fails these checks foura_auto returns an error envelope. |
| `forceProxy` | boolean | no | Always reach the target through a rotating proxy, never from FourA's own egress. Default true (the target never sees FourA's origin IP). Send false to allow the |
| `timeout_ms` | integer | no | Total time budget in ms for the WHOLE operation - auto fires several internal attempts and they must all fit inside this. Default 120000, max 180000. Auto porti |
| `ignoreProxies` | array | no | Exits to AVOID - base36 proxy ids (like "4DZ3VE") or proxy URLs. Auto skips a warm session on one of these and tells its internal proxy search to avoid them too |
| `offload_large` | boolean | no | If true, response bodies >= 50KB are written to disk and returned as a resource_link instead of inlined. Saves token context but requires a client that supports |
| `returnSession` | boolean | no | Return the {proxy, cookies, userAgent} session triple of the winning session so you can replay it through foura_single / foura_proxy later. Default true. Send f |
| `followRedirects` | integer | no | Follow up to N redirects on the cheap (direct / proxy) rungs so a 301/302 lands on the real content instead of being returned as-is. Default 5; 0 = don't follow |

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": "foura_auto",
    "arguments": {
      "url": "<url>"
    }
  }
}
```

## Why foura_auto is rated Low

While web scraping via proxy or automated browser can raise ethical and legal concerns (terms of service violations, potential for reconnaissance on restricted sites), the tool's core function is data retrieval with no side effects on the target or agent's own systems.

From the tool's own definition: "The tool is described as 'Give a URL, get the content back' and is explicitly positioned as 'the default first choice for any page when you just want the data'. It fetches and returns page content without modifying or deleting data."

Risk signals: Accepts URL/endpoint input (url) · High parameter count (20 properties)

## Use case

AI agents call foura_auto to retrieve information from 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 Mcp:

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

## Other tools on Mcp (3)

- `foura_proxy` — Execute — https://policylayer.com/tools/ai-foura-mcp/foura-proxy.md
- `foura_single` — Read — https://policylayer.com/tools/ai-foura-mcp/foura-single.md
- `foura_browser` — Write — https://policylayer.com/tools/ai-foura-mcp/foura-browser.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=ai-foura-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/ai-foura-mcp