Follow redirects only within the MCP endpoint's origin (#3397)

This commit is contained in:
Max 2026-09-04 23:43:38 +01:00 • committed by GitHub
commit c6762e821c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 1029 additions and 205 deletions

View file

@ -83,6 +83,8 @@ The first time `Client` sends a request, the server answers `401`. The provider
After that it is quiet. Tokens come out of storage, an expired access token is refreshed with the refresh token, and only when none of that works does it run the flow again.
One transport rule applies to all of these requests: like the MCP request they run inside, they follow a redirect only when it stays on the same origin and keeps the method (a trailing-slash 307/308, say), and treat any other redirect as that URL not answering.
You wrote none of it. Two keyword arguments remain (`client_metadata_url` and `validate_resource_url`), and this file needs neither. `client_metadata_url` is the one worth knowing about; it gets its own section below.
### Try it

View file

@ -29,7 +29,7 @@ Pass a URL string and you get **Streamable HTTP**, the transport you deploy behi
--8<-- "docs_src/client_transports/tutorial002.py"
```
That is the whole production client. `Client` wraps the URL in `streamable_http_client(...)` for you, on top of an `httpx2.AsyncClient` configured the way MCP needs: `follow_redirects=True`, a 30-second timeout for connect/write/pool, and a 300-second read timeout because the server may hold a response stream open.
That is the whole production client. `Client` wraps the URL in `streamable_http_client(...)` for you, on top of an `httpx2.AsyncClient` configured the way MCP needs: a 30-second timeout for connect/write/pool, and a 300-second read timeout because the server may hold a response stream open.
!!! check
A `Client` you have constructed is **not** connected. Construction only picks the transport;
@ -45,7 +45,7 @@ That is the whole production client. `Client` wraps the URL in `streamable_http_
The moment you need an `Authorization` header, a cookie, a proxy, mTLS, or a different timeout, build the `httpx2.AsyncClient` yourself and hand it to `streamable_http_client`:
```python title="client.py" hl_lines="8-14"
```python title="client.py" hl_lines="8-13"
--8<-- "docs_src/client_transports/tutorial003.py"
```
@ -75,9 +75,30 @@ environment variables or pass an explicit `verify=ssl_context` to your `httpx2.A
!!! info
`httpx2` keeps the familiar `httpx` API, so if you know `httpx` you already know how to do auth,
proxies, event hooks, retries and connection limits here. The SDK adds nothing on top and takes
nothing away. It is also where OAuth plugs in:
nothing away, except [redirect handling](#redirects). It is also where OAuth plugs in:
`httpx2.AsyncClient(auth=OAuthClientProvider(...))`. That whole flow is **[OAuth clients](oauth-clients.md)**.
### Redirects
The transport connects to the URL you gave it, and only that origin.
* A `307`/`308` redirect that stays on the same scheme, host and port is followed, and so is `http://` → `https://` on the same host. That covers the usual `/mcp` → `/mcp/` trailing-slash redirect.
* A redirect anywhere else is **not** followed. The call fails with:
```text
MCPError: Redirect to https://other.example.com/mcp not followed; use that URL as the endpoint if it is the intended server
```
If that URL is the server you meant, put it in your config. If it isn't, the server or a proxy in front of it is misconfigured.
This holds for any `httpx2.AsyncClient` you pass in: its `follow_redirects` setting is not consulted for MCP requests, in either direction. The SDK's OAuth providers apply the same rule to their own requests.
!!! tip
`Redirect to http://… not followed: it would downgrade this HTTPS endpoint to plain HTTP` means the
server sits behind a TLS-terminating proxy it doesn't know about and is issuing `http://` redirects.
That is fixed on the server (**[Deploy & scale](../run/deploy.md#behind-a-tls-terminating-proxy)**),
or by using the exact `https://…/` URL the message suggests.
## stdio
A **stdio** server is a subprocess. The client launches it, writes JSON-RPC to its stdin and reads JSON-RPC from its stdout. It is how a desktop host runs a server on your machine: a host *is* this code plus a UI, and **[Connect to a real host](../get-started/real-host.md)** is the same relationship seen from the host's side, as a config file.
@ -115,6 +136,7 @@ A **transport** is any async context manager that yields a `(read, write)` pair
* `Client(mcp)` (the server object) connects in memory. Use it for tests and for embedding.
* `Client("http://.../mcp")` (a URL) connects over Streamable HTTP, the production transport.
* Headers, auth, proxies and timeouts belong on an `httpx2.AsyncClient` you pass to `streamable_http_client(url, http_client=...)`. There is no `headers=` keyword.
* Redirects are followed only within the URL's own origin (a trailing-slash `307`/`308`), plus `http`→`https` on the same host. Anything else fails with `Redirect to … not followed`; configure the final URL.
* stdio is `Client(StdioServerParameters(...))`. Wrap it in `stdio_client(...)` yourself only to redirect the child's stderr.
* The subprocess gets an allow-listed environment, not yours; `env=` adds to it.
* A transport is anything you can `async with x as (read, write)`. `Client` hands anything that isn't a server object, a URL or `StdioServerParameters` straight to that protocol.