UTC
High

@andrea9293/mcp-documentation-server: Web UI API binds to all interfaces without authentication by default

CVE-2026-54504 · GHSA-6f5r-5672-72j7 · published 2026-07-15 · updated 2026-07-18

Severity
High
CVSS score
8.8
Chance of exploitation (EPSS)
0.57%
Fixed in
1.13.1
  • Exploitation Public proof of concept
  • Automatable No
  • Technical impact Total
  • CISA SSVC
What it is

This is a missing-authentication and unsafe-default network exposure issue for the Web UI/API. A network-reachable attacker can access the document-management API without credentials. Depending on what the user stores in the documentation server, this may allow: reading document titles, previews, and full document contents; searching across the entire document corpus; inserting attacker-controlled documents into the corpus; deleting documents; tampering with the user's local knowledge base used by the MCP assistant. This can affect users who run the MCP server on laptops, workstations, dev VMs, or hosts connected to shared networks, VPNs, Docker bridges, or other routable local networks.

What to do

Upgrade @andrea9293/mcp-documentation-server to 1.13.1 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.

Affected
PackageRegistryAffectedFixed in
@andrea9293/mcp-documentation-servernpm= 1.13.01.13.1

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].