alihan/mcpdoc
1
0
Fork 0
mirror of https://github.com/langchain-ai/mcpdoc.git synced 2025-10-19 03:18:14 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix: redirect domain check

Browse Source
This commit is contained in:
aliyanishfaq
2025-07-22 13:00:32 -07:00
parent 49a0662332
commit 60a3cffbff
1 changed files with 23 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
mcpdoc/main.py
View File

@@ -229,7 +229,7 @@ def create_server(
@server.tool(description=fetch_docs_description)
async def fetch_docs(url: str) -> str:
nonlocal domains
nonlocal domains, follow_redirects
url = url.strip()
# Handle local file paths (either as file:// URLs or direct filesystem paths)
if not _is_http_or_https(url):
@@ -259,19 +259,29 @@ def create_server(
response.raise_for_status()
content = response.text
# Check for meta refresh tag which indicates a client-side redirect
match = re.search(
r'<meta http-equiv="refresh" content="[^;]+;\s*url=([^"]+)"',
content,
re.IGNORECASE,
)
if follow_redirects:
# Check for meta refresh tag which indicates a client-side redirect
match = re.search(
r'<meta http-equiv="refresh" content="[^;]+;\s*url=([^"]+)"',
content,
re.IGNORECASE,
)
if match:
redirect_url = match.group(1)
new_url = urljoin(str(response.url), redirect_url)
response = await httpx_client.get(new_url, timeout=timeout)
response.raise_for_status()
content = response.text
if match:
redirect_url = match.group(1)
new_url = urljoin(str(response.url), redirect_url)
if "*" not in domains and not any(
new_url.startswith(domain) for domain in domains
):
return (
"Error: Redirect URL not allowed. Must start with one of the following domains: "
+ ", ".join(domains)
)
response = await httpx_client.get(new_url, timeout=timeout)
response.raise_for_status()
content = response.text
return markdownify(content)
except (httpx.HTTPStatusError, httpx.RequestError) as e: