This DeepSeek MCP server, developed by David Montgomery, enables seamless integration of DeepSeek's advanced language models with MCP-compatible applications like Claude Desktop. Built with TypeScript and leveraging the Model Context Protocol SDK, it provides a chat completion tool with customizable parameters such as model selection, temperature control, and token limits. The implementation focuses on simplifying access to DeepSeek's powerful AI capabilities through a standardized interface. It's particularly useful for developers and researchers looking to incorporate state-of-the-art language models into their applications without dealing directly with DeepSeek's API intricacies, enabling use cases like AI-assisted writing, code generation, and complex reasoning tasks.
아직 리뷰가 없습니다. 첫 번째 리뷰를 작성해 보세요!
대화에 참여하려면 로그인하세요
DeepSeek V4 chat. Defaults to deepseek-v4-flash. Supports parameters: thinking (object with type enabled or disabled), reasoning_effort (string: low, high, max), JSON output, function tools, logprobs, streaming, and conversation memory.
Stateless native Responses API calls with text or structured input. Supports reasoning effort controls, function tools, server-side web search, structured output, and semantic streaming.
DeepSeek V4 Pro FIM completion. Defaults to deepseek-v4-pro.
Reads the live DeepSeek model list.
Reads account balance and availability.
Clears an in-memory conversation.
Lists in-memory conversation IDs.
