# curl_advanced

Execute curl with custom arguments (advanced usage)

Agent View of the PolicyLayer registry record for `curl_advanced`. HTML page: https://policylayer.com/tools/247arjun-mcp-curl/curl-advanced

## Facts

- Tool: `curl_advanced`
- Server: Curl MCP Server (`247arjun/mcp-curl`) — https://policylayer.com/tools/247arjun-mcp-curl.md
- Homepage: https://github.com/247arjun/mcp-curl
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

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

## Why curl_advanced is rated High

This tool runs curl commands with user-supplied arguments, making it an Execute category risk. Confidence is high because the description explicitly states 'Execute'. Severity is critical because custom arguments could be weaponized to invoke any HTTP method (GET, POST, PUT, DELETE, PATCH) against any endpoint, exfiltrate data, modify external systems, or trigger destructive operations.

From the tool's own definition: "Tool name 'curl_advanced' with description 'Execute curl with custom arguments' — the word 'Execute' directly indicates code/command execution."

## Use case

AI agents invoke curl_advanced to trigger actions in Curl MCP Server. 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 Curl MCP Server:

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

## Other tools on Curl MCP Server (5)

- `curl_delete` — Destructive — https://policylayer.com/tools/247arjun-mcp-curl/curl-delete.md
- `curl_download` — Read — https://policylayer.com/tools/247arjun-mcp-curl/curl-download.md
- `curl_get` — Read — https://policylayer.com/tools/247arjun-mcp-curl/curl-get.md
- `curl_post` — Write — https://policylayer.com/tools/247arjun-mcp-curl/curl-post.md
- `curl_put` — Write — https://policylayer.com/tools/247arjun-mcp-curl/curl-put.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=247arjun-mcp-curl · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/247arjun-mcp-curl