Skip to content
Fencer Intel
high 8.1

CVE-2025-66416 json

DNS Rebinding Protection Disabled by Default in Model Context Protocol Python SDK for Servers Running on Localhost

published 11mo ago modified 22d ago also GHSA-9h52-p55h-vw2f , PYSEC-2026-1617 , EUVD-2025-200273

cvss
8.1
version 3.1, NVD
cisa kev
Not listed
not in CISA's catalog
epss
0.5%
EPSS 0.5% chance of exploitation in 30 days, percentile 45%
public exploits
0
none known

Summary

The MCP Python SDK, called `mcp` on PyPI, is a Python implementation of the Model Context Protocol (MCP). Prior to version 1.23.0, tThe Model Context Protocol (MCP) Python SDK does not enable DNS rebinding protection by default for HTTP-based servers. When an HTTP-based MCP server is run on localhost without authentication using FastMCP with streamable HTTP or SSE transport, and has not configured TransportSecuritySettings, a malicious website could exploit DNS rebinding to bypass same-origin policy restrictions and send requests to the local MCP server. This could allow an attacker to invoke tools or access resources exposed by the MCP server on behalf of the user in those limited circumstances. Note that running HTTP-based MCP servers locally without authentication is not recommended per MCP security best practices. This issue does not affect servers using stdio transport. This vulnerability is fixed in 1.23.0.

Patch / fix

  • pypi mcp 1.23.0
  • lfprojects mcp_python_sdk 1.23.0

Is CVE-2025-66416 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2025-66416 updated cvss 8.1

mcp: DNS Rebinding Protection Disabled by Default in Model Context Protocol Python SDK

  • Red Hat OpenShift Lightspeed openshift-lightspeed/lightspeed-service-api-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-llama-stack-core-rhel9
    affected: workaround, no fix available
  • Red Hat Ansible Automation Platform 2.6 ansible-automation-platform-26 1768887865, ansible-automation-platform-26 1768915992
    fixed: vendor fix RHSA-2026:1596
  • Red Hat OpenShift AI 2.25 rhoai v2.25.1-1765354568
    fixed: vendor fix RHSA-2025:23531
  • Red Hat OpenShift AI 3.3 rhoai 1770277795
    fixed: vendor fix RHSA-2026:3713
  • Red Hat Satellite 6.18 satellite 1767868827
    fixed: vendor fix RHSA-2026:0629
  • Red Hat Ansible Automation Platform 2 ansible-automation-platform/ee-minimal-rhel8, ansible-automation-platform/ee-minimal-rhel9, ansible-automation-platform-24/de-minimal-rhel8, ansible-automation-platform-24/de-minimal-rhel9, ansible-automation-platform-24/ee-minimal-rhel8, ansible-automation-platform-24/ee-minimal-rhel9, +25 more Red Hat Ansible Automation Platform 2.6 ansible-automation-platform 1768951346, ansible-automation-platform 1768951348, ansible-automation-platform-26 1768509220, ansible-automation-platform-26 1768846975, ansible-automation-platform-26 1768853828, ansible-automation-platform-26 1768858596, +20 more Red Hat OpenShift AI 2.25 rhoai 0.0-1763988459, rhoai v2.25.1-1764757768, rhoai v2.25.1-1764757769, rhoai v2.25.1-1764757770, rhoai v2.25.1-1764757772, rhoai v2.25.1-1764757773, +35 more Red Hat OpenShift AI 3.3 rhoai 1769162595, rhoai 1769436305, rhoai 1769519975, rhoai 1770735854, rhoai 1770754585, rhoai 1770754605, +71 more
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
total
Assessed
11mo ago

Exploit prediction

0.54% chance of exploitation in the next 30 days, higher than 45% of all scored CVEs (FIRST EPSS, 2026-11-09).

CVSS scores

assigned by version score vector
CNA 4.0 7.6 CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N
CNA 4.0 7.6 CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
NVD 3.1 8.1 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:N

Affected packages

ecosystem package affected fixed in
pypi mcp
<1.23.0
1.23.0

Affected products

  • modelcontextprotocol python-sdk

Classification

Weakness
  • CWE-1188 Initialization of a Resource with an Insecure Default
  • CWE-350 Reliance on Reverse DNS Resolution for a Security-Critical Action

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.