[{"_1":2,"_373":-5,"_374":-5},"loaderData",{"_3":4,"_29":30,"_300":301},"root",{"_5":6,"_14":15},"toasts",[7],{"_8":9,"_10":11,"_12":13},"uid","01999981-6fdb-7075-9dd1-12cb90fd7187","title","This MCP server does not support inspection","type","error","visitor",{"_16":17,"_18":19},"viewportWidth",1280,"visitorSession",{"_20":21,"_23":24,"_25":-5,"_26":27,"_28":-5},"attributes",[22],"bot","id",17216360,"membership","referenceId","01999741-5648-746d-aa76-377bfd37ef27","userAccount","routes/_public/mcp/servers/~namespace/~slug/_pages/_layout",{"_31":32,"_69":-5,"_70":33,"_34":71,"_218":219,"_299":203},"availableLocales",[33,45,52,57,62],{"_34":35,"_38":42,"_43":44},"mcpServer",{"_36":37,"_38":39,"_40":41},"description","This server enables AI assistants (CLINE, Cursor, Windsurf, Claude Desktop) to share a common knowledge base through Retrieval Augmented Generation (RAG), providing consistent information access across multiple tools.","name","Shared Knowledge MCP Server","readme","# Shared Knowledge MCP Server\n\nThis is a knowledge base MCP server that can be used in common with various AI assistants (CLINE, Cursor, Windsurf, Claude Desktop). It utilizes Retrieval Augmented Generation (RAG) to realize efficient information search and utilization. By sharing the knowledge base between multiple AI assistant tools, it provides consistent information access.\n\n## Features\n\n* A common knowledge base can be used across multiple AI assistants\n* High-precision information retrieval using RAG\n* Type-safe implementation using TypeScript\n* Supports multiple vector stores (HNSWLib, Chroma, Pinecone, Milvus)\n* Extensibility through abstracted interfaces\n\n## install\n\n```bash\ngit clone https://github.com/yourusername/shared-knowledge-mcp.git\ncd shared-knowledge-mcp\nnpm install\n```\n\n## setting\n\nThe MCP server settings are added to the configuration file of each AI assistant.\n\n### VSCode (for CLINE/Cursor)\n\n`~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json` :\n\n```json\n{\n \"mcpServers\": {\n \"shared-knowledge-base\": {\n \"command\": \"node\",\n \"args\": [\"/path/to/shared-knowledge-mcp/dist/index.js\"],\n \"env\": {\n \"KNOWLEDGE_BASE_PATH\": \"/path/to/your/rules\",\n \"OPENAI_API_KEY\": \"your-openai-api-key\",\n \"SIMILARITY_THRESHOLD\": \"0.7\",\n \"CHUNK_SIZE\": \"1000\",\n \"CHUNK_OVERLAP\": \"200\",\n \"VECTOR_STORE_TYPE\": \"hnswlib\"\n }\n }\n }\n}\n```\n\n### Examples of using Pinecone\n\n```json\n{\n \"mcpServers\": {\n \"shared-knowledge-base\": {\n \"command\": \"node\",\n \"args\": [\"/path/to/shared-knowledge-mcp/dist/index.js\"],\n \"env\": {\n \"KNOWLEDGE_BASE_PATH\": \"/path/to/your/rules\",\n \"OPENAI_API_KEY\": \"your-openai-api-key\",\n \"VECTOR_STORE_TYPE\": \"pinecone\",\n \"VECTOR_STORE_CONFIG\": \"{\\\"apiKey\\\":\\\"your-pinecone-api-key\\\",\\\"environment\\\":\\\"your-environment\\\",\\\"index\\\":\\\"your-index-name\\\"}\"\n }\n }\n }\n}\n```\n\n### Claude Desktop\n\n`~/Library/Application Support/Claude/claude_desktop_config.json` :\n\n#### Example using HNSWLib (default)\n\n```json\n{\n \"mcpServers\": {\n \"shared-knowledge-base\": {\n \"command\": \"node\",\n \"args\": [\"/path/to/shared-knowledge-mcp/dist/index.js\"],\n \"env\": {\n \"KNOWLEDGE_BASE_PATH\": \"/path/to/your/docs\",\n \"OPENAI_API_KEY\": \"your-openai-api-key\",\n \"SIMILARITY_THRESHOLD\": \"0.7\",\n \"CHUNK_SIZE\": \"1000\",\n \"CHUNK_OVERLAP\": \"200\",\n \"VECTOR_STORE_TYPE\": \"hnswlib\",\n \"VECTOR_STORE_CONFIG\": \"{}\"\n },\n \"disabled\": false,\n \"autoApprove\": []\n }\n }\n}\n```\n\n#### Examples of using Weaviate\n\n```json\n{\n \"mcpServers\": {\n \"shared-knowledge-base\": {\n \"command\": \"node\",\n \"args\": [\"/path/to/shared-knowledge-mcp/dist/index.js\"],\n \"env\": {\n \"KNOWLEDGE_BASE_PATH\": \"/path/to/your/docs\",\n \"OPENAI_API_KEY\": \"your-openai-api-key\",\n \"SIMILARITY_THRESHOLD\": \"0.7\",\n \"CHUNK_SIZE\": \"1000\",\n \"CHUNK_OVERLAP\": \"200\",\n \"VECTOR_STORE_TYPE\": \"weaviate\",\n \"VECTOR_STORE_CONFIG\": \"{\\\"url\\\":\\\"http://localhost:8080\\\",\\\"className\\\":\\\"Document\\\",\\\"textKey\\\":\\\"content\\\"}\"\n },\n \"disabled\": false,\n \"autoApprove\": []\n }\n }\n}\n```\n\n**Note** : If you are using Weaviate, you must first start the Weaviate server, which can be done with the following command:\n\n```bash\n./start-weaviate.sh\n```\n\n## development\n\n### Start the development server\n\n```bash\nnpm run dev\n```\n\n### Build\n\n```bash\nnpm run build\n```\n\n### Running in Production\n\n```bash\nnpm start\n```\n\n## Available Tools\n\n### rag\\_search\n\nSearch for information in the knowledge base.\n\n#### Search Request\n\n```typescript\ninterface SearchRequest {\n // 検索クエリ（必須）\n query: string;\n \n // 返す結果の最大数（デフォルト: 5）\n limit?: number;\n \n // 検索のコンテキスト（オプション）\n context?: string;\n \n // フィルタリングオプション（オプション）\n filter?: {\n // ドキュメントの種類でフィルタリング（例: [\"markdown\", \"code\"]）\n documentTypes?: string[];\n \n // ソースパスのパターンでフィルタリング（例: \"*.md\"）\n sourcePattern?: string;\n };\n \n // 結果に含める情報（オプション）\n include?: {\n metadata?: boolean; // メタデータを含める\n summary?: boolean; // 要約を生成\n keywords?: boolean; // キーワードを抽出\n relevance?: boolean; // 関連性の説明を生成\n };\n}\n```\n\n#### Usage Example\n\nBasic search:\n\n```typescript\nconst result = await callTool(\"rag_search\", {\n query: \"コミットメッセージ��フォーマット\",\n limit: 3\n});\n```\n\nAdvanced Search:\n\n```typescript\nconst result = await callTool(\"rag_search\", {\n query: \"コミットメッセージのフォーマット\",\n context: \"Gitの使い方について調査中\",\n filter: {\n documentTypes: [\"markdown\"],\n sourcePattern: \"git-*.md\"\n },\n include: {\n summary: true,\n keywords: true,\n relevance: true\n }\n});\n```\n\n#### Search Results\n\n```typescript\ninterface SearchResult {\n // 検索クエリに関連する文書の内容\n content: string;\n \n // 類似度スコア（0-1）\n score: number;\n \n // ソースファイルのパス\n source: string;\n \n // 位置情報\n startLine?: number; // 開始行\n endLine?: number; // 終了行\n startColumn?: number; // 開始桁\n endColumn?: number; // 終了桁\n \n // ドキュメントの種類（例: \"markdown\", \"code\", \"text\"）\n documentType?: string;\n \n // 追加情報（include オプションで指定した場合のみ）\n summary?: string; // コンテンツの要約\n keywords?: string[]; // 関連キーワード\n relevance?: string; // 関連性の説明\n metadata?: Record; // メタデータ\n}\n```\n\n#### Response example\n\n````json\n{\n \"results\": [\n {\n \"content\": \"# コミットメッセージのフォーマット\\n\\n以下の形式でコミットメッセージを記述してください：\\n\\n```\\n(): \\n\\n\\n\\n

MCP directory API