{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_6kavx6328uta","handle":"rbt-mcp-server","url":"https://wellknown.network/agents/rbt-mcp-server","links":{"self":"https://wellknown.network/agents/rbt-mcp-server/record.json","html":"https://wellknown.network/agents/rbt-mcp-server","markdown":"https://wellknown.network/agents/rbt-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/rbt-mcp-server","status":"https://wellknown.network/api/v1/agents/rbt-mcp-server/status","claim":"https://wellknown.network/agents/rbt-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/rbt-mcp-server/claim.json","badge":"https://wellknown.network/agents/rbt-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/rbt-mcp-server/history","tools":"https://wellknown.network/api/v1/agents/rbt-mcp-server/tools"},"ard":{"identifier":"urn:air::server:rbt-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"rbt-mcp-server","summary":"MCP Server for Graphiti memory and document chunking with intelligent Markdown processing.","description":"# KnowledgeSmith MCP Server\n\nMCP Server for **Graphiti memory and document chunking**. Previously included RBT document editing tools (now archived).\n\n## 📦 Archive Notice\n\n### RBT Document Editor Tools (Archived 2025-10-09)\n\nThe RBT document editing功能已於 2025-10-09 封存，改用原生 Claude Code Read/Edit/Write 工具以降低維護成本和 token 使用。\n\n**封存內容：**\n- document_service.py - 文件服務\n- document_parser.py - 文件解析器\n- 11 個 editor MCP 工具（get_outline, read_content, update_block 等）\n- templates/ - 文件模板\n- cache.py - 文件快取\n\n**保留功能：**\n- ✅ chunking/ - 文件分塊與同步功能\n- ✅ graphiti_tools.py - Graphiti 記憶體功能（8 個工具）\n\n**如何恢復封存的代碼：**\n```bash\n# 查看封存版本\ngit show v-with-editor\n\n# 恢復特定檔案\ngit checkout v-with-editor -- rbt_mcp_server/document_service.py\n\n# 或建立分支使用完整封存版本\ngit checkout -b restore-editor v-with-editor\n```\n\n## 🎯 Current Features\n\n### Graphiti Knowledge Graph Integration\n- **Intelligent Chunking**: Automatically split documents into semantic chunks based on document structure (sections for RBT, H3 headings for Markdown)\n- **Incremental Sync**: Only update changed chunks, preserving unchanged content\n- **Neo4j Backend**: Store document chunks as episodes in Graphiti knowledge graph\n- **graphiti-memory Compatible**: Drop-in replacement with same search_nodes/search_facts API\n- **8 MCP Tools**: add_document, search_memory_nodes, search_memory_facts, get_episodes, delete_episode, get_entity_edge, delete_entity_edge, clear_graph\n\n## 📦 Installation\n\n### Prerequisites\n\n**1. Setup Neo4j Database**\n\nUsing Docker (recommended):\n```bash\ndocker run \\\n  -p 7474:7474 \\\n  -p 7687:7687 \\\n  -e NEO4J_AUTH=neo4j/your-password \\\n  --name neo4j \\\n  neo4j:latest\n```\n\nVerify at: http://localhost:7474\n\n**2. Get OpenAI API Key**\n\nRequired for Graphiti embeddings and graph operations.\n\n### Install MCP Server\n\n**Option 1: Install from source (uv)**\n\n```bash\n# Clone repository\ngit clone https://github.com/yourusername/KnowledgeSmith.git\ncd KnowledgeSmith\n\n# Install with uv\nuv pip install -e .\n```\n\n**Option 2: Direct installation**\n\n``…","publisher":null,"homepage":"https://github.com/yourusername/KnowledgeSmith","repository":"https://github.com/yourusername/KnowledgeSmith","version":"0.3.2","license":"MIT","protocols":["mcp"],"tags":["document-editor","llm","mcp","rbt","token-optimization"],"pricing":null,"endpoints":[{"url":"pypi:rbt-mcp-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"derived"}],"categories":["dev","knowledge"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"rbt-mcp-server","registry":"pypi","observedAt":"2026-10-28T21:26:17.825Z","publishedAt":"2025-10-15T03:02:34.264617Z","latestVersion":"0.3.2"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"rbt-mcp-server","url":"https://pypi.org/project/rbt-mcp-server/","firstSeenAt":"2026-09-10T11:26:07.884Z","fetchedAt":"2026-10-28T21:24:13.220Z","normalizedAt":"2026-10-28T21:24:13.220Z"}]},"firstSeenAt":"2026-09-10T11:26:07.884Z","updatedAt":"2026-10-28T21:26:17.825Z"}