CVE-2026-54504: CWE-306: Missing Authentication for Critical Function in andrea9293 mcp-documentation-server
Description
MCP Documentation Server is a local-first document management and semantic search server for AI coding agents. From 1.13.0 until 1.13.1, the automatically started Web UI in src/server.ts calls startWebServer in src/web-server.ts with START_WEB_UI enabled by default and WEB_PORT set to 3080. startWebServer uses app.listen(PORT) without a host, which binds the unauthenticated document-management API to all interfaces rather than localhost. A network-reachable client can invoke GET /api/documents, GET /api/documents/:id, POST /api/documents, POST /api/search-all, DELETE /api/documents/:id, and GET /api/config without credentials to enumerate and read documents, search the corpus, insert or delete documents, and tamper with the MCP assistant's knowledge base. The service must be reachable from the attacker's LAN, VM network, container bridge, VPN, or another routed network, and the issue does not provide remote code execution. This issue is fixed in 1.13.1.
CVSS v3.1
Score 8.8high
Affected software
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
MCP Documentation Server versions >=1.13.0 and <1.13.1 start a Web UI server that listens on all interfaces (0.0.0.0) without requiring authentication. This exposes several API endpoints (GET /api/documents, GET /api/documents/:id, POST /api/documents, POST /api/search-all, DELETE /api/documents/:id, GET /api/config) to any client on the same network or reachable network segment. An attacker can enumerate, read, insert, delete documents, and modify the assistant's knowledge base. The vulnerability does not allow remote code execution and requires network-level access to the service. The issue is resolved in version 1.13.1.
Potential Impact
An attacker with network access to the affected MCP Documentation Server can perform unauthorized document enumeration, reading, insertion, deletion, and configuration changes. This compromises confidentiality, integrity, and availability of the document management system and the AI assistant's knowledge base. However, remote code execution is not possible via this vulnerability.
Mitigation Recommendations
Upgrade to version 1.13.1 or later where the Web UI server no longer binds to all interfaces without authentication. Until patched, restrict network access to the service to trusted hosts only to prevent unauthorized access.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-6f5r-5672-72j7
- Osv Schema Version
- 1.4.0
- Aliases
- ["CVE-2026-54504"]
- Ecosystems
- ["npm"]
- Database Specific Severity
- HIGH
- Cvss Version
- 3.1
Threat ID: 6a58b40468715ace43d67007
Added to database: 07/16/2026, 10:35:48 UTC
Last enriched: 09/17/2026, 22:13:54 UTC
Last updated: 10/17/2026, 06:48:18 UTC
Views: 222
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.