CVE-2025-66416
Published: 02 December 2025
Summary
CVE-2025-66416 is a high-severity Initialization of a Resource with an Insecure Default (CWE-1188) vulnerability in Lfprojects Mcp Python Sdk. Its CVSS base score is 7.6 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Drive-by Compromise (T1189); ranked at the 16.7th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Protocol-Specific Risks risk domain.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-200273
Vulnerability details
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.…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Protocol-Specific Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: mcp, model context protocol
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
The lack of DNS rebinding protection enables drive-by compromise (T1189) via malicious websites and network boundary bridging (T1599.001) to bypass the browser's same-origin policy, allowing attackers to send requests to the unauthenticated local HTTP MCP server and invoke tools or access resources.
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Requires documented secure initialization practices and avoidance of insecure defaults in configuration baselines.
Reviewing and updating baseline when components are installed or upgraded prevents initialization with insecure defaults.
Requiring explicit configuration to minimal functionality overrides insecure defaults that would otherwise enable excess capabilities.
Tailoring replaces or augments insecure default initializations with system-specific values and compensating controls before deployment.
Central configuration overrides or replaces insecure default initializations that would otherwise be left unchanged on each system.
SCRM practices during acquisition and configuration management address insecure default initializations shipped by vendors.
Scans detect resources initialized with insecure defaults that create exploitable conditions.
Instruction on secure initialization of security controls prevents leaving resources with insecure defaults after installation.