Live › vulnerability › CVE-2026-116685
Go to dashboardThe official Model Context Protocol Python SDK's HTTP and SSE clients follow redirects to a different origin and forward caller-supplied credential headers, and for 307 or 308 responses the request body. An attacker who can change a trusted endpoint's redirect target can collect those credentials and data.
Summary written from the sources below. Check the originals before acting.
First seen by InfraStack 2026-10-27 20:33 UTC. All times on this page are UTC.
Teams whose Python code uses the MCP client paths (streamable HTTP, SSE, OAuth, ClientSessionGroup) against remote MCP servers while sending custom credential headers or request bodies. Exposure also needs a trusted endpoint that can be made to redirect to a host the attacker controls. Teams that only run MCP servers, or use the SDK over stdio, are not in the described path.
| Product | Ecosystem | Affected | Fixed in |
|---|---|---|---|
| mcp | pypi | >= 2.0.0, < 2.2.0 | 2.2.0 |
| mcp | pypi | >= 1.8.0, < 1.30.0 | 1.30.0 |
pip show mcp and compare it to the fixed versions.streamablehttp_client, streamable_http_client, sse_client, ClientSessionGroup, or create_mcp_http_client in your code that passes custom auth headers.mcp Python package to 1.30.0 (1.x line) or 2.2.0 (2.x line).Each row is the first time that source carried this signal. The analyst’s rows are its own findings.
In affected versions, the SDK's Streamable HTTP and SSE client transports followed HTTP redirects to any host. If the configured MCP endpoint answered with a redirect to a different origin:
X-API-Key credential) were sent to that origin, and307 or 308 redirect the request body was re-sent there too.The SDK's OAuth client providers followed redirects on their own discovery, registration and token requests in the same way.
A lone Authorization bearer header was not exposed; the HTTP library already drops it on cross-origin redirects.
Anyone able to make an endpoint you trust redirect elsewhere (a stale redirect to a lapsed domain, a misrouted proxy rule, redirect logic an attacker can influence) could capture that material. A server that is itself malicious gains nothing this way; it already receives your requests directly.
Yes, if your code uses the SDK as an MCP client over HTTP through any of:
streamable_http_client (on 2.x also Client given an http:// or https:// URL)streamablehttp_client or sse_clientClientSessionGroup with HTTP server parameterscreate_mcp_http_client helperThis includes an HTTP client you passed in yourself with follow_redirects=True.
Affected versions: 1.8.0 through 1.29.1, and 2.0.0 through 2.1.1.
Not affected:
follow_redirects left at its default of FalseUpgrade to mcp 1.30.0 (1.x) or 2.2.0 (2.x) or later; no code changes are needed.
The transports, and the OAuth providers' own requests, now follow a redirect only when it stays on the endpoint's origin (same scheme, host and port, or an http to https upgrade on the same host) and keeps the request method. Any other redirect is not followed and the request fails with an error naming the target (MCPError on 2.x, httpx.HTTPStatusError on 1.x), whichever HTTP client the transport uses. The internal create_mcp_http_client helper no longer turns redirect following on, so code calling it directly now receives the redirect response instead.
If your client currently reaches its server through a redirect to another host, including a server that needs no credentials, it will stop connecting after the upgrade: set the endpoint URL to the redirect's target.
Until you can upgrade, supply your own HTTP client with follow_redirects left at False (http_client= on streamable_http_client; httpx_client_factory= on sse_client and streamablehttp_client; ClientSessionGroup has no such parameter). If a client may already have followed a redirect to a host you do not control, rotate the credentials it carried.
This restores what this advisory fixes: redirects to any host are followed again, carrying your custom headers and, on 307/308, the request body, OAuth token requests included. Prefer setting the endpoint URL to the redirect's target. If you cannot, and you accept forwarding credentials to the redirect target, give the transport an HTTP client that follows redirects regardless of what the SDK asks for:
import httpx2 # on 1.x: import httpx and subclass httpx.AsyncClient instead
class FollowRedirectsAnyway(httpx2.AsyncClient):
"""Follows redirects to ANY origin. Deliberately gives up the SDK's same-origin protection."""
async def send(self, request, *, follow_redirects=False, **kwargs):
return await super().send(request, follow_redirects=True, **kwargs)
http_client = FollowRedirectsAnyway(timeout=httpx2.Timeout(30, read=300))
# streamable_http_client(url, http_client=http_client)
# sse_client / streamablehttp_client take a factory instead:
def client_factory(headers=None, timeout=None, auth=None):
return FollowRedirectsAnyway(headers=headers, auth=auth,
timeout=timeout if timeout is not None else httpx2.Timeout(30, read=300))
# sse_client(url, httpx_client_factory=client_factory)
The redirect handling is then the HTTP library's own, as before the fix: a lone Authorization header is still dropped on cross-origin hops and 301/302/303 become GET. It is not something the SDK supports or tests.
This page as .md · .json · in your agent: get_signal("CVE-2026-116685")
NVD data is provided by NIST and is public domain · GitHub Advisory Database, CC-BY 4.0. Posts quoted belong to their authors.