[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"cc-detail-mcp-servers-arikusi-deepseek-mcp-server":3},{"id":4,"slug":5,"type":6,"title":7,"summary":8,"description_md":9,"install_command":10,"install_method":11,"source_url":12,"source_type":13,"github_repo":14,"github_stars":15,"github_last_commit_at":16,"language":17,"tags":18,"use_cases":24,"status":25,"submitted_by_ip":26,"approved_at":27,"view_count":28,"copy_count":28,"created_at":29,"updated_at":29,"quality_score":30,"discovered_via":31},"900b6785-1e55-423a-968c-4f03c36abf2d","arikusi-deepseek-mcp-server","mcp_server","DeepSeek MCP Server","MCP server for DeepSeek V4 with chat, reasoning, function calling, and cost tracking.","DeepSeek MCP Server exposes DeepSeek V4 models through the Model Context Protocol for Claude Code and other MCP clients.\n\nIt supports `deepseek-v4-flash` and `deepseek-v4-pro`, multi-turn sessions, function calling, thinking mode, JSON output, and cost tracking. The README also notes MCP resources for models, config, and usage, plus tools for chat, FIM, and session management.\n\nThe project can be used remotely through a hosted HTTP endpoint or locally over stdio. The README says it is compatible with Claude Code, Gemini CLI, Cursor, Windsurf, and other MCP-compatible clients.","claude mcp add -s user deepseek npx @arikusi\u002Fdeepseek-mcp-server -e DEEPSEEK_API_KEY=your-key-here","npx","https:\u002F\u002Fgithub.com\u002Farikusi\u002Fdeepseek-mcp-server","github","arikusi\u002Fdeepseek-mcp-server",17,"2026-07-06T05:36:58+00:00","en",[19,20,21,22,23],"mcp","deepseek","claude-code","ai-model","function-calling",[],"approved",null,"2026-07-10T06:50:07.966+00:00",0,"2026-07-10T06:50:07.975026+00:00",8,"awesome-list"]