MCP Knowledge Service
Enables semantic search and management of development knowledge including global rules, project documentation, and references through vector-based search using libSQL. Features Tailscale-secured access control and tools for searching, browsing, and organizing development resources across multiple channels.
README
MCP Knowledge Service
MCP-based knowledge and rules suite for Tailscale networks with semantic search via libSQL vectors.
Features
- MCP Tools:
rules.search,project.search,refs.list, and more - Semantic Search: Vector-based search using libSQL with OpenAI embeddings
- Multi-Channel: Support for multiple MCP channels (rules, projects, refs)
- Tailscale Security: Identity-based access control via Tailscale Serve
- Vector Database: libSQL with native vector support for ANN search
Quick Start
-
Setup Environment:
./scripts/setup.sh -
Configure Environment: Edit
.envwith your configuration:LIBSQL_URL=file:./data/knowledge.db OPENAI_API_KEY=your-openai-api-key -
Development:
npm run dev # Start development server npm run build # Build for production npm test # Run tests npm run lint # Lint code
Architecture
src/mcp/- MCP server and tool implementationssrc/db/- Database schema, connections, and migrationssrc/http/- REST API endpoints for ingestionsrc/auth/- Tailscale identity and access controlsrc/utils/- Shared utilities and helpers
MCP Tools
Rules Service
rules.search(q, k?, tags?)- Search global development rulesrules.get(id)- Get specific rule by IDrules.tags()- List all available rule tags
Project Service
project.search(project, q, k?)- Search within project docsproject.browse(project, path?)- Browse project structureproject.contextPack(project, facets?)- Get curated context bundle
References Service
refs.list(tags?, limit?)- List references with optional tag filterrefs.add(title, url, note?, tags_csv?)- Add new referencerefs.findByTag(tag)- Find references by specific tag
Database Schema
The service uses libSQL with vector support:
rules_global- Global AI development rules with embeddingsproject_docs- Project-specific documentation with embeddingsrefs- Quick reference links and documentationaccess_tiers- User access control and permissionsaudit_log- Query audit trail and metrics
Development Status
See TODO.md for current development phases and tasks.
Related
- Memory subsystem development:
/home/ubuntu/mem - Design documentation:
docs/memory-design.md
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。