{"id":26648340,"url":"https://github.com/DMontgomery40/deepseek-mcp-server","last_synced_at":"2025-03-25T00:01:59.463Z","repository":{"id":273577618,"uuid":"920179950","full_name":"DMontgomery40/deepseek-mcp-server","owner":"DMontgomery40","description":"Model Context Protocol server for DeepSeek's advanced language models","archived":false,"fork":false,"pushed_at":"2025-03-13T05:18:15.000Z","size":153,"stargazers_count":122,"open_issues_count":2,"forks_count":12,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-20T22:45:04.702Z","etag":null,"topics":["deepseek-api","deepseek-chat","deepseek-r1","deepseek-v3","mcp","model-context-protocol","r1"],"latest_commit_sha":null,"homepage":"https://buymeacoffee.com/dmontg","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DMontgomery40.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-01-21T17:45:36.000Z","updated_at":"2025-03-20T12:32:06.000Z","dependencies_parsed_at":"2025-01-21T18:45:38.525Z","dependency_job_id":"e978f49e-b58b-422c-af29-a233edd5af6a","html_url":"https://github.com/DMontgomery40/deepseek-mcp-server","commit_stats":null,"previous_names":["dmontgomery40/mcp_deepseek"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DMontgomery40%2Fdeepseek-mcp-server","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DMontgomery40%2Fdeepseek-mcp-server/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DMontgomery40%2Fdeepseek-mcp-server/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DMontgomery40%2Fdeepseek-mcp-server/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DMontgomery40","download_url":"https://codeload.github.com/DMontgomery40/deepseek-mcp-server/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245372377,"owners_count":20604491,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deepseek-api","deepseek-chat","deepseek-r1","deepseek-v3","mcp","model-context-protocol","r1"],"created_at":"2025-03-25T00:01:45.215Z","updated_at":"2025-03-25T00:01:59.355Z","avatar_url":"https://github.com/DMontgomery40.png","language":"JavaScript","funding_links":[],"categories":["LLM Bridges","📚 Projects (1974 total)","Community Servers","AI Services","Content Creation","Mcp Server Directories \u0026 Lists","MCP Servers","🌐 Web Development","Table of Contents","🗂️ Extensions by Category"],"sub_categories":["Trading \u0026 Exchanges","MCP Servers","Other MCP Servers","AI Services","🤖 AI Systems"],"readme":"# DeepSeek MCP Server\n\nA Model Context Protocol (MCP) server for the DeepSeek API, allowing seamless integration of DeepSeek's powerful language models with MCP-compatible applications like Claude Desktop.\n\n## *Anonymously*  use DeepSeek API  --  Only a proxy is seen on the other side \n\n\u003ca href=\"https://glama.ai/mcp/servers/asht4rqltn\"\u003e\u003cimg width=\"380\" height=\"200\" src=\"https://glama.ai/mcp/servers/asht4rqltn/badge\" alt=\"DeepSeek Server MCP server\" /\u003e\u003c/a\u003e\n\n\n[![npm version](https://img.shields.io/npm/v/deepseek-mcp-server)](https://www.npmjs.com/package/deepseek-mcp-server)\n[![npm downloads](https://img.shields.io/npm/dm/deepseek-mcp-server)](https://www.npmjs.com/package/deepseek-mcp-server)\n[![GitHub issues](https://img.shields.io/github/issues/DMontgomery40/deepseek-mcp-server)](https://github.com/DMontgomery40/deepseek-mcp-server/issues)\n[![GitHub forks](https://img.shields.io/github/forks/DMontgomery40/deepseek-mcp-server)](https://github.com/DMontgomery40/deepseek-mcp-server/network)\n[![GitHub stars](https://img.shields.io/github/stars/DMontgomery40/deepseek-mcp-server)](https://github.com/DMontgomery40/deepseek-mcp-server/stargazers)\n[![GitHub license](https://img.shields.io/github/license/DMontgomery40/deepseek-mcp-server?color=blue)](https://github.com/DMontgomery40/deepseek-mcp-server/blob/main/LICENSE)\n\n## Installation\n\n### Installing via Smithery\n\nTo install DeepSeek MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@dmontgomery40/deepseek-mcp-server):\n\n```bash\nnpx -y @smithery/cli install @dmontgomery40/deepseek-mcp-server --client claude\n```\n\n### Manual Installation\n```bash\nnpm install -g deepseek-mcp-server\n```\n### Usage with Claude Desktop\n\nAdd this to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"deepseek\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"deepseek-mcp-server\"\n      ],\n      \"env\": {\n        \"DEEPSEEK_API_KEY\": \"your-api-key\"\n      }\n    }\n  }\n}\n```\n\n## Features\n\n\u003e Note: The server intelligently handles these natural language requests by mapping them to appropriate configuration changes. You can also query the current settings and available models:\n\n- User: \"What models are available?\"\n  - Response: Shows list of available models and their capabilities via the models resource.\n- User: \"What configuration options do I have?\"\n  - Response: Lists all available configuration options via the model-config resource.\n- User: \"What is the current temperature setting?\"\n  - Response: Displays the current temperature setting.\n- User: \"Start a multi-turn conversation. With the following settings: model: 'deepseek-chat', make it not too creative, and \n   allow 8000 tokens.\"\n  - Response: *Starts a multi-turn conversation with the specified settings.*\n\n### Automatic Model Fallback if R1 is down\n\n- If the primary model (R1) is down (called `deepseek-reasoner` in the server), the server will automatically attempt to try with v3 (called `deepseek-chat` in the server) \n\u003e Note: You can switch back and forth anytime as well, by just giving your prompt and saying \"use `deepseek-reasoner`\" or \"use `deepseek-chat`\"\n- V3 is recommended for general purpose use, while R1 is recommended for more technical and complex queries, primarily due to speed and token usage\n\n###  Resource discovery for available models and configurations:\n   * Custom model selection\n   * Temperature control (0.0 - 2.0)\n   * Max tokens limit\n   * Top P sampling (0.0 - 1.0)\n   * Presence penalty (-2.0 - 2.0)\n   * Frequency penalty (-2.0 - 2.0)\n\n## Enhanced Conversation Features\n\n**Multi-turn conversation support:**\n* Maintains complete message history and context across exchanges\n* Preserves configuration settings throughout the conversation\n* Handles complex dialogue flows and follow-up chains automatically\n\nThis feature is particularly valuable for two key use cases:\n\n1. **Training \u0026 Fine-tuning:**\n   Since DeepSeek is open source, many users are training their own versions. The multi-turn support provides properly formatted conversation data that's essential for training high-quality dialogue models.\n\n2. **Complex Interactions:**\n   For production use, this helps manage longer conversations where context is crucial:\n   * Multi-step reasoning problems\n   * Interactive troubleshooting sessions\n   * Detailed technical discussions\n   * Any scenario where context from earlier messages impacts later responses\n\nThe implementation handles all context management and message formatting behind the scenes, letting you focus on the actual interaction rather than the technical details of maintaining conversation state.\n\n\n\n\n## Testing with MCP Inspector\n\nYou can test the server locally using the MCP Inspector tool:\n\n1. Build the server:\n   ```bash\n   npm run build\n   ```\n\n2. Run the server with MCP Inspector:\n   ```bash\n   # Make sure to specify the full path to the built server\n   npx @modelcontextprotocol/inspector node ./build/index.js\n   ```\n\nThe inspector will open in your browser and connect to the server via stdio transport. You can:\n- View available tools\n- Test chat completions with different parameters\n- Debug server responses\n- Monitor server performance\n\nNote: The server uses DeepSeek's R1 model (deepseek-reasoner) by default, which provides state-of-the-art performance for reasoning and general tasks.\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FDMontgomery40%2Fdeepseek-mcp-server","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FDMontgomery40%2Fdeepseek-mcp-server","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FDMontgomery40%2Fdeepseek-mcp-server/lists"}