<?xml version='1.0' encoding='UTF-8'?>
<?xml-stylesheet href="/static/style.xsl" type="text/xsl"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
  <id>https://db.gcve.eu/rss/recent/all/10</id>
  <title>Most recent entries from all</title>
  <updated>2026-11-03T15:50:29.673321+00:00</updated>
  <author>
    <name>Vulnerability-Lookup</name>
    <email>info@gcve.eu</email>
  </author>
  <link href="https://db.gcve.eu" rel="alternate"/>
  <generator uri="https://lkiesow.github.io/python-feedgen" version="1.0.0">python-feedgen</generator>
  <subtitle>Contains only the most 10 recent entries.</subtitle>
  <entry>
    <id>https://db.gcve.eu/vuln/brew-cycode-cve-2026-116685</id>
    <title>BREW-cycode-CVE-2026-116685 — Model Context Protocol Python SDK: HTTP client transports followed cross-origin redirects carrying custom headers and b…</title>
    <updated>2026-11-03T15:50:29.925265+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> Homebrew: cycode</p>
<p>### Summary
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:</p>
<p>- custom headers set on the client (for example an `X-API-Key` credential) were sent to that origin, and
- on a `307` or `308` redirect the request body was re-sent there too.</p>
<p>The SDK's OAuth client providers followed redirects on their own discovery, registration and token requests in the same way.</p>
<p>A lone `Authorization` bearer header was not exposed; the HTTP library already drops it on cross-origin redirects.</p>
<p>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.</p>
<p>### Am I affected?
Yes, if your code uses the SDK as an MCP client over HTTP through any of:</p>
<p>- `streamable_http_client` (on 2.x also `Client` given an `http://` or `https://` URL)
- `streamablehttp_client` or `sse_client`
- `ClientSessionGroup` with HTTP server parameters
- the internal `create_mcp_http_client` helper</p>
<p>This includes an HTTP client you passed in yourself with `follow_redirects=True`.</p>
<p>Affected versions: 1.8.0 through 1.29.1, and 2.0.0 through 2.1.1.</p>
<p>Not affected:</p>
<p>- MCP servers
- stdio clients
- a client you supplied with `follow_redirects` left at its def…</p></div>
    </content>
    <link href="https://db.gcve.eu/vuln/brew-cycode-cve-2026-116685"/>
  </entry>
  <entry>
    <id>https://db.gcve.eu/vuln/fkie_cve-2026-116685</id>
    <title>fkie_cve-2026-116685</title>
    <updated>2026-11-03T15:50:29.925392+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml">
        <p>The Model Context Protocol Python SDK is the official Python SDK for Model Context Protocol servers and clients. From 1.8.0 until 1.30.0 and 2.2.0, streamable_http_client, streamablehttp_client, sse_client, ClientSessionGroup, OAuth, and create_mcp_http_client client paths enable follow_redirects and follow redirects to a different origin, forwarding caller-supplied custom credential headers and, for 307 or 308 responses, the request body. An attacker who can influence a trusted endpoint's redirect destination can receive that material. This issue is fixed in versions 1.30.0 and 2.2.0.</p>
      </div>
    </content>
    <link href="https://db.gcve.eu/vuln/fkie_cve-2026-116685"/>
  </entry>
  <entry>
    <id>https://db.gcve.eu/vuln/ghsa-5h93-6whr-6q8j</id>
    <title>GHSA-5h93-6whr-6q8j — Model Context Protocol Python SDK: HTTP client transports followed cross-origin redirects carrying custom headers and b…</title>
    <updated>2026-11-03T15:50:29.925441+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> PyPI: mcp</p>
<p>### Summary
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:</p>
<p>- custom headers set on the client (for example an `X-API-Key` credential) were sent to that origin, and
- on a `307` or `308` redirect the request body was re-sent there too.</p>
<p>The SDK's OAuth client providers followed redirects on their own discovery, registration and token requests in the same way.</p>
<p>A lone `Authorization` bearer header was not exposed; the HTTP library already drops it on cross-origin redirects.</p>
<p>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.</p>
<p>### Am I affected?
Yes, if your code uses the SDK as an MCP client over HTTP through any of:</p>
<p>- `streamable_http_client` (on 2.x also `Client` given an `http://` or `https://` URL)
- `streamablehttp_client` or `sse_client`
- `ClientSessionGroup` with HTTP server parameters
- the internal `create_mcp_http_client` helper</p>
<p>This includes an HTTP client you passed in yourself with `follow_redirects=True`.</p>
<p>Affected versions: 1.8.0 through 1.29.1, and 2.0.0 through 2.1.1.</p>
<p>Not affected:</p>
<p>- MCP servers
- stdio clients
- a client you supplied with `follow_redirects` left at its def…</p></div>
    </content>
    <link href="https://db.gcve.eu/vuln/ghsa-5h93-6whr-6q8j"/>
  </entry>
</feed>
