UTC
HighExploited in the wild (CISA KEV)

LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback

CVE-2026-59822 · GHSA-7488-6r32-c95q · published 2026-07-22

Severity
High
CVSS score
8.8
Chance of exploitation (EPSS)
0.84%
Fixed in
1.84.0

Known exploited

CISA added this to its Known Exploited Vulnerabilities catalog on 2026-09-02; US federal agencies had until 2026-09-16 to act. CISA's required action: Apply mitigations in accordance with vendor instructions, ensuring compliance with CISA’s BOD 26-04 Prioritizing Security Updates Based on Risk.

  • Exploitation Exploited in the wild
  • Automatable Yes
  • Technical impact Partial
  • CISA SSVC
What it is

LiteLLM's MCP Streamable HTTP endpoint could allow an unauthenticated attacker to establish an authenticated MCP session using an arbitrary Bearer token. The MCP auth handler supported OAuth2 passthrough for upstream MCP servers, but the fallback path could replace failed LiteLLM key validation with an empty UserAPIKeyAuth() object. This allowed requests with a fabricated Authorization header to reach MCP tooling without a valid LiteLLM key. An attacker could use this to list and call configured MCP tools and access connected services exposed through MCP.

What to do

Upgrade litellm to 1.84.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

The issue is fixed in 1.84.0. We recommend upgrading to 1.84.0 or later.

If you cannot upgrade yet

If upgrading is not immediately possible, disable MCP routes or block access to /mcp/ and related MCP endpoints at your reverse proxy or API gateway.

Affected
PackageRegistryAffectedFixed in
litellmPyPI< 1.84.01.84.0
Downstream in the Official MCP Registry

1 registered MCP server installs an affected version today, by the dependency versions a fresh install resolves.

  • io.github.Brightdotdev/darwin-raglitellm@1.83.14
See the trace →

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].