Bridge to DeepSeek AI models with chat, reasoning, multi-turn sessions, function calling, and cost tracking.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
process.env. You'll be asked to provide them before it can run.DEEPSEEK_API_KEY— "Authorization": "Bearer ${}"DEEPSEEK_BASE_URLDEFAULT_MODEL— deepseek-chat Default model for requestsENABLE_MULTIMODAL— Multimodal Ready: Content part types for text + image input (enable with =true)FALLBACK_ENABLED— Fallback can be disabled with =false.HTTP_PORT— 3000 HTTP server port (when TRANSPORT=http)MAX_MESSAGE_LENGTH— 100000 Maximum message content length (characters)MAX_RETRIES— 2 Maximum retry count for failed requestsMAX_SESSIONS— 100 Maximum number of concurrent sessionsMAX_SESSION_MESSAGES— 200 Max messages per session (sliding window)REQUEST_TIMEOUT— 60000 Request timeout in millisecondsSESSION_TTL_MINUTES— 30 Session time-to-live in minutesSHOW_COST_INFO— true Show cost info in responsesSKIP_CONNECTION_TEST— false Skip startup API connection testTRANSPORT— HTTP Transport: Self-hosted remote access via Streamable HTTP with =http[](https://m8ven.ai/mcp/arikusi-deepseek-mcp-server-64yzv0)