Critical severity · published Jun 13, 2026
CVE-2026-11624
The Model Context Protocol has a security warning advising servers to validate the "Origin" header on all incoming connections to prevent DNS rebinding attacks
9.4
CVSS
0.2%
EPSS
No
On KEV
Description
The Model Context Protocol has a security warning advising servers to validate the "Origin" header on all incoming connections to prevent DNS rebinding attacks. Prior to the v0.25.0 release, users had no way to validate the origin's host. In v0.25.0, a new "--allowed-hosts" flag was introduced alongside the existing "--allowed-origins" flag, enabling users to specify permitted hosts at server startup. Both flags default to "*", allowing users to implement strict access controls as needed without breaking existing setups. If either flag is set to "*", the server will output a startup warning about potential vulnerabilities. Documentation has also been updated to highlight these security considerations.
Exploitation
Is it being used?
Exploit prediction (EPSS)0.2% · higher than 12% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
MT
MCP Toolbox for Databases · Google
before 0.25.0 · source: vendor
Affected product
MT
MCP Toolbox for Databases
Google
More from MCP Toolbox for Databases
9.8
CVE-2026-14537
Authorization Bypass in MCP Toolbox Legacy HTTP Endpoints
9.4
CVE-2026-9739
Vulnerable to DNS rebinding attacks when using SSE (http://b/499408790)
9.1
CVE-2026-11720
Path Traversal in googleapis/mcp-toolbox HTTP Tool URL Builder
9.1
CVE-2026-11718
An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox
9.1
CVE-2026-11717
An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox