# CVE-2026-30623: BerriAI LiteLLM remote code execution in MCP server creation

Source: https://junglewise.ai/threats/cve-2026-30623-berriai-litellm-remote-code-execution-in-mcp-server-creation  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-07-15. Updated: 2026-07-15  
License: CC BY 4.0 with a link back

CVE-2026-30623 · Severity: info · CVSS 8.8 · Published 2026-07-15

LiteLLM, a tool used to manage and connect various AI models, contains a security flaw in how it handles Model Context Protocol (MCP) servers. An authorized user could provide a specially crafted configuration that forces the server to execute unauthorized operating system commands. This could allow an attacker to take full control of the LiteLLM process, potentially leading to data theft or service disruption.

Technologies: [Berriai LiteLLM](https://junglewise.ai/threats/technologies/litellm). Vendors: [Berriai](https://junglewise.ai/threats/vendors/berriai).

## Quick answers

**Is CVE-2026-30623 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-30623 being exploited in the wild.

**How severe is CVE-2026-30623?** Informational severity, with a CVSS score of 8.8, published 15 July 2026.

**Which products and versions are affected?** Berriai LiteLLM < 1.83.7-stable.

**Is there a fix for CVE-2026-30623?** A patch was published on 2026-04-21: LiteLLM released fix in v1.83.6-nightly and v1.83.7-stable Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-30623 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-30623?** Check whether you run Berriai LiteLLM 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.

## Technical details

LiteLLM versions prior to 1.83.7-stable are vulnerable to command injection within the MCP server creation functionality. The vulnerability exists because the application accepts JSON configurations for MCP servers using the 'stdio' transport and passes the 'command' and 'args' fields directly to a subprocess launcher without validation. An authenticated attacker with permissions to create MCP servers or access preview endpoints (such as /mcp-rest/test/connection) can execute arbitrary shell commands with the privileges of the LiteLLM process. The fix introduces a command allowlist (e.g., npx, uvx, python) and restricts access to the preview endpoints to users with the PROXY_ADMIN role.

## Affected products

- BerriAI LiteLLM < 1.83.7-stable

## Timeline

- 2026-04-15: disclosed: Initial advisory by OX Security regarding MCP SDK vulnerabilities
- 2026-04-21: patched: LiteLLM released fix in v1.83.6-nightly and v1.83.7-stable
- 2026-07-15: advisory: CVE-2026-30623 published to NVD

## References

- [https://docs.litellm.ai/blog/mcp-stdio-command-injection-april-2026](https://docs.litellm.ai/blog/mcp-stdio-command-injection-april-2026)
- [https://github.com/BerriAI/litellm](https://github.com/BerriAI/litellm)
- [https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/](https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/)

## Related threats

- [LiteLLM arbitrary local file read via vertex_ai_credentials](https://junglewise.ai/threats/litellm-internal-user-viewer-arbitrary-local-file-read-via-vertex-ai-649a7475)
- [LiteLLM reflected XSS in SSO debug callback endpoint](https://junglewise.ai/threats/litellm-vulnerable-to-reflected-xss-in-sso-debug-callback-38154651)
- [LiteLLM proxy authentication bypass via reused crypto context](https://junglewise.ai/threats/cve-2026-114612-litellm-is-a-proxy-server-ai-gateway-to-call-llm-apis-in-openai)
- [BerriAI LiteLLM improper authorization in secret resolution](https://junglewise.ai/threats/cve-2026-108575-a-vulnerability-has-been-found-in-berriai-litellm-up-to-1-94-0)
- [BerriAI LiteLLM authorization bypass in spend tracking](https://junglewise.ai/threats/cve-2026-108574-a-flaw-has-been-found-in-berriai-litellm-up-to-1-95-0-affected)