fix(fetch): accept socks proxy alias

src/fetch/pyproject.toml

@@ -16,7 +16,7 @@ classifiers = [
     "Programming Language :: Python :: 3.10",
 ]
 dependencies = [
-    "httpx>=0.27",
+    "httpx[socks]>=0.27",
     "markdownify>=0.13.1",
     "mcp>=1.1.3",
     "protego>=0.3.1",

src/fetch/src/mcp_server_fetch/server.py

@@ -1,3 +1,4 @@
+import os
 from typing import Annotated, Tuple
 from urllib.parse import urlparse, urlunparse
 
@@ -63,6 +64,37 @@ def get_robots_txt_url(url: str) -> str:
     return robots_url
 
 
+def normalize_proxy_url(proxy_url: str | None) -> str | None:
+    if proxy_url is None:
+        return None
+
+    if proxy_url.lower().startswith("socks://"):
+        return f"socks5://{proxy_url[len('socks://'):]}"
+
+    return proxy_url
+
+
+def proxy_url_for_request(url: str, proxy_url: str | None = None) -> str | None:
+    if proxy_url:
+        return normalize_proxy_url(proxy_url)
+
+    scheme = urlparse(url).scheme.lower()
+    proxy_keys = []
+    if scheme == "https":
+        proxy_keys.extend(("HTTPS_PROXY", "https_proxy"))
+    elif scheme == "http":
+        proxy_keys.extend(("HTTP_PROXY", "http_proxy"))
+    proxy_keys.extend(("ALL_PROXY", "all_proxy"))
+
+    for key in proxy_keys:
+        env_proxy = os.environ.get(key)
+        normalized = normalize_proxy_url(env_proxy)
+        if normalized != env_proxy:
+            return normalized
+
+    return None
+
+
 async def check_may_autonomously_fetch_url(url: str, user_agent: str, proxy_url: str | None = None) -> None:
     """
     Check if the URL can be fetched by the user agent according to the robots.txt file.
@@ -72,7 +104,7 @@ async def check_may_autonomously_fetch_url(url: str, user_agent: str, proxy_url:
 
     robot_txt_url = get_robots_txt_url(url)
 
-    async with AsyncClient(proxy=proxy_url) as client:
+    async with AsyncClient(proxy=proxy_url_for_request(robot_txt_url, proxy_url)) as client:
         try:
             response = await client.get(
                 robot_txt_url,
@@ -116,7 +148,7 @@ async def fetch_url(
     """
     from httpx import AsyncClient, HTTPError
 
-    async with AsyncClient(proxy=proxy_url) as client:
+    async with AsyncClient(proxy=proxy_url_for_request(url, proxy_url)) as client:
         try:
             response = await client.get(
                 url,

src/fetch/tests/test_server.py

@@ -10,6 +10,7 @@
     check_may_autonomously_fetch_url,
     fetch_url,
     DEFAULT_USER_AGENT_AUTONOMOUS,
+    proxy_url_for_request,
 )
 
 
@@ -324,3 +325,35 @@ async def test_fetch_with_proxy(self):
 
             # Verify AsyncClient was called with proxy
             mock_client_class.assert_called_once_with(proxy="http://proxy.example.com:8080")
+
+    @pytest.mark.asyncio
+    async def test_fetch_accepts_socks_proxy_alias(self):
+        """Test that socks:// proxy URLs are accepted as SOCKS5 proxies."""
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_response.text = '{"data": "test"}'
+        mock_response.headers = {"content-type": "application/json"}
+
+        with patch("httpx.AsyncClient") as mock_client_class:
+            mock_client = AsyncMock()
+            mock_client.get = AsyncMock(return_value=mock_response)
+            mock_client_class.return_value.__aenter__ = AsyncMock(return_value=mock_client)
+            mock_client_class.return_value.__aexit__ = AsyncMock(return_value=None)
+
+            await fetch_url(
+                "https://example.com/data",
+                DEFAULT_USER_AGENT_AUTONOMOUS,
+                proxy_url="socks://127.0.0.1:2080/"
+            )
+
+            mock_client_class.assert_called_once_with(proxy="socks5://127.0.0.1:2080/")
+
+    def test_fetch_accepts_socks_proxy_from_environment(self, monkeypatch):
+        """Test that invalid socks:// environment proxies are normalized."""
+        monkeypatch.delenv("HTTPS_PROXY", raising=False)
+        monkeypatch.delenv("https_proxy", raising=False)
+        monkeypatch.delenv("ALL_PROXY", raising=False)
+        monkeypatch.delenv("all_proxy", raising=False)
+        monkeypatch.setenv("ALL_PROXY", "socks://127.0.0.1:2080/")
+
+        assert proxy_url_for_request("https://example.com/data") == "socks5://127.0.0.1:2080/"