# curl_get

Make an HTTP GET request using curl

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

## Facts

- Tool: `curl_get`
- Server: Curl MCP Server (`247arjun/mcp-curl`) — https://policylayer.com/tools/247arjun-mcp-curl.md
- Homepage: https://github.com/247arjun/mcp-curl
- 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": "curl_get",
    "arguments": {}
  }
}
```

## Why curl_get is rated Low

HTTP GET requests are inherently read operations that retrieve data without side effects. However, severity is medium rather than low because curl requests can interact with arbitrary URLs and APIs, which could leak sensitive data, cause information disclosure, or be used for reconnaissance if the AI agent is compromised or given malicious instructions.

From the tool's own definition: "HTTP GET request uses curl to retrieve data from web APIs and content without modifying state. The sibling tools (curl_post, curl_put, curl_delete) confirm curl_get is the read operation."

## Use case

AI agents call curl_get to retrieve information from Curl MCP Server 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 Curl MCP Server:

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

## Other tools on Curl MCP Server (5)

- `curl_delete` — Destructive — https://policylayer.com/tools/247arjun-mcp-curl/curl-delete.md
- `curl_advanced` — Execute — https://policylayer.com/tools/247arjun-mcp-curl/curl-advanced.md
- `curl_download` — Read — https://policylayer.com/tools/247arjun-mcp-curl/curl-download.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