Is CVE-2026-52869 exploited in the wild?

No. Junglewise Threat Intelligence has no report of CVE-2026-52869 being exploited in the wild.

How severe is CVE-2026-52869?

High severity, with a CVSS score of 7.1, published 15 July 2026.

Which products and versions are affected?

Anthropic Model Context Protocol <= 1.27.1; Model Context Protocol Python SDK < 1.27.2; mcp (PyPI) ECOSYSTEM:introduced=0,fixed=1.27.2.

Is there a fix for CVE-2026-52869?

Yes. mcp (PyPI): upgrade to 1.27.2 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

How is CVE-2026-52869 attacked?

It is attacked over the network, in a software library.

Am I affected by CVE-2026-52869?

Check whether you run Anthropic Model Context Protocol, Model Context Protocol Python SDK or mcp (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

CVE-2026-52869: modelcontextprotocol mcp authorization bypass in SSE and HTTP transports

Q: Is there a fix for CVE-2026-52869?

Yes. mcp (PyPI): upgrade to 1.27.2 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

Q: How is CVE-2026-52869 attacked?

It is attacked over the network, in a software library.

Q: Am I affected by CVE-2026-52869?

Check whether you run Anthropic Model Context Protocol, Model Context Protocol Python SDK or mcp (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

CVE-2026-52869 · Severity: high · CVSS 7.1 · Published 2026-07-15

The Model Context Protocol (MCP) Python SDK contains a security flaw in how it handles web-based communication sessions. An attacker who obtains a valid session ID can send unauthorized commands or intercept data from another user's session, even if they have different login credentials. This could lead to unauthorized data access or the ability to perform actions on behalf of other users in applications using this toolkit.

Technologies: Anthropic Model Context Protocol, Model Context Protocol Python SDK, mcp (PyPI). Vendors: Anthropic, Model Context Protocol, PyPI.

Quick answers

Is CVE-2026-52869 exploited in the wild?: No. Junglewise Threat Intelligence has no report of CVE-2026-52869 being exploited in the wild.
How severe is CVE-2026-52869?: High severity, with a CVSS score of 7.1, published 15 July 2026.
Which products and versions are affected?: Anthropic Model Context Protocol <= 1.27.1; Model Context Protocol Python SDK < 1.27.2; mcp (PyPI) ECOSYSTEM:introduced=0,fixed=1.27.2.
Is there a fix for CVE-2026-52869?: Yes. mcp (PyPI): upgrade to 1.27.2 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
How is CVE-2026-52869 attacked?: It is attacked over the network, in a software library.
Am I affected by CVE-2026-52869?: Check whether you run Anthropic Model Context Protocol, Model Context Protocol Python SDK or mcp (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

How to fix

mcp (PyPI): upgrade to 1.27.2 or later
```
pip install "mcp>=1.27.2"
```

Technical details

An authorization bypass (CWE-639) exists in the SSE and Streamable HTTP server transports of the MCP Python SDK. The `mcp.server.sse.SseServerTransport` and `mcp.server.streamable_http_manager.StreamableHTTPSessionManager` components look up sessions using only the session identifier (via query parameters or headers) without validating the associated authentication principal (OAuth client ID, issuer, or subject). A network-based attacker with knowledge of a session UUID can inject JSON-RPC messages into that session or read responses. The vulnerability is mitigated in version 1.27.2, which implements principal verification for each session request.

Affected products

Model Context Protocol (MCP) mcp <= 1.27.1

Identifiers

CVE-2026-52869
GHSA-jpw9-pfvf-9f58
PYSEC-2026-3482

Timeline

2026-06-05: disclosed
2026-07-15: advisory: NVD publication date
2026-07-16: patched: GitHub Advisory published/updated with patch information

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.