Vulnerability in @arikusi/deepseek-mcp-server (CVE-2026-55605)
Summary
Vulnerability in @arikusi/deepseek-mcp-server (CVE-2026-55605). Risk of unauthorized operations or information disclosure. Exploitable via POST /mcp. Mitigation: upgrade to 1.8.0 or later.
Original description
The description as published by the source.
DeepSeek MCP Server is an MCP server for DeepSeek V4. Starting in version 1.4.2 and prior to version 1.8.0, the self-hosted HTTP transport of @arikusi/deepseek-mcp-server exposes POST /mcp without any authentication: createMcpExpressApp is called without an authProvider and no middleware guards the route, so any network-reachable client can issue an unauthenticated initialize request and obtain a valid MCP session identifier. In reproduced testing against commit 5e1302171e99, an unauthenticated client was able to initialize a session, enumerate tools, and invoke the local deepseek_sessions tool with no credentials. The same unauthenticated session also exposes deepseek_chat, whose handler uses the server-side DEEPSEEK_API_KEY when self-hosted deployments configure one. This issue applies to self-hosted HTTP mode, not the separately documented hosted BYOK endpoint in README.md, which expects an Authorization: Bearer ... header. Upstream self-hosted container assets enable HTTP mode by default (Dockerfile) and publish port 3000 (docker-compose.yml). Version 1.8.0 contains a patch for this issue.
Source: NIST National Vulnerability Database NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-55605 has been found in @arikusi/deepseek-mcp-server.
Attackers can target a specific entry point like POST /mcp over the network to misuse the product.
Risk of unauthorized operations or information disclosure. CVSS score: 5.3/10.
What to do: upgrade @arikusi/deepseek-mcp-server to 1.8.0 or later.
If unsure, ask your IT team or search "@arikusi/deepseek-mcp-server CVE-2026-55605" on the vendor's site.
CVE-2026-55605 (@arikusi/deepseek-mcp-server) — CWE-306 / CVSS v3 5.3
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Attack surface: POST /mcp / createMcpExpressApp / authProvider / initialize
Patched: 1.8.0 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
A vulnerability (CWE-306) exists in @arikusi/deepseek-mcp-server. Attackers reach the vulnerable code path via POST /mcp without authentication.
Check the vendor advisory for the affected versions of @arikusi/deepseek-mcp-server. Attack surface: POST /mcp / createMcpExpressApp / authProvider / initialize.
Severity: Medium (CVSS 5.3/10). Risk of unauthorized operations or information disclosure.
Update to 1.8.0.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual POST /mcp requests with malformed payloads or SQL meta-characters. Run grep -r '@arikusi/deepseek-mcp-server' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r '@arikusi/deepseek-mcp-server' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
@arikusi/deepseek-mcp-serverを grep し、稼働しているサービス・バージョンを把握する。 -
2Hunt for indicators of compromise detect
grep 'POST /mcp' /var/log/nginx/access.log | grep -E '(unusual_payload|sqli_pattern)'アクセスログで
POST /mcpへの異常なリクエスト (不正な認証ヘッダ・SQLメタ文字)を過去 30〜90日分捜索。WAF/SIEM があれば該当パスのアラート発火履歴を確認。 -
3Apply patch patch
Upgrade @arikusi/deepseek-mcp-server to 1.8.0ステージング環境で 1.8.0 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスと、Step 2 で見つけた異常検知の続報チェックを含めること。
-
4Post-deployment verification verify
Replay attack against POST /mcp on staging to confirm patch closes the vectorパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番では Step 2 と同じログクエリでアラート再発が無いか継続監視。
Affected packages
References
- advisory github.com
- advisory nvd.nist.gov
- advisory github.com
- package github.com
- web github.com
- web github.com
- web github.com
- web github.com
- web github.com