Attack Chain

1. Network Discovery: An attacker scans local networks (LAN, VM networks, Docker bridges) for open ports, specifically identifying systems listening on port 3080/TCP.
2. Service Identification: Upon finding an open port 3080/TCP, the attacker sends a benign HTTP GET request to a known public endpoint like /api/config to confirm that the @andrea9293/mcp-documentation-server Web UI/API is running and network-accessible.
3. Unauthenticated Access: The attacker attempts to interact with document management API endpoints (e.g., /api/documents, /api/search-all) without providing any authentication credentials (e.g., no Authorization header).
4. Information Disclosure: The attacker sends unauthenticated HTTP GET requests to /api/documents and /api/documents/:id to enumerate and read the content of stored documents.
5. Data Manipulation: The attacker sends unauthenticated HTTP POST requests to /api/documents to insert new, attacker-controlled documents into the server's corpus.
6. Corpus Search: The attacker leverages the unauthenticated /api/search-all endpoint with specific queries to search across the entire document corpus, potentially extracting sensitive information.
7. Data Destruction: The attacker sends unauthenticated HTTP DELETE requests to /api/documents/:id to delete existing documents from the server.
8. Impact on Knowledge Base: Through these actions, the attacker can read, add, modify, or delete documents, effectively tampering with or destroying the user's local knowledge base used by the MCP assistant.

Impact

The described vulnerability allows a network-reachable attacker to gain full administrative access to the document management API without any credentials. This can lead to significant impact depending on the nature of the data stored in the documentation server. Attackers can read sensitive document titles, previews, and full contents, search the entire corpus for specific information, insert malicious or misleading documents, and delete existing documents. This could result in information disclosure, data integrity compromise, and data loss. Users running the MCP server on shared networks, virtual machines, or local development environments are particularly vulnerable, as an attacker on the same network segment can exploit this flaw to corrupt or exfiltrate the user's local knowledge base.

Recommendation

• Deploy the Sigma rule to detect suspicious API access: Deploy the Detect Unauthenticated Access to MCP Documentation Server API rule to your SIEM to alert on any non-localhost access to the sensitive API endpoints (/api/documents, /api/search-all, /api/config) on port 3080.
• Monitor webserver logs: Monitor webserver logs for HTTP requests to /api/documents, /api/search-all, and /api/config originating from non-localhost IP addresses, particularly on port 3080.
• Implement network segmentation: Restrict network access to port 3080 on hosts running the @andrea9293/mcp-documentation-server to only trusted internal IP addresses or localhost as described in CVE-2026-54504.
• Apply vendor patches: Refer to the advisory at https://github.com/advisories/GHSA-6f5r-5672-72j7 for any future patches or configuration guidance from the vendor to bind the service to 127.0.0.1 by default or enable authentication.