Smart Connections MCP Server
Smart Connections MCP Server
让 Claude 真正拥有对 Obsidian 库的语义记忆。 这是一个 MCP 服务器,通过含义搜索你的笔记——复用 Smart Connections Obsidian 插件已生成的嵌入,并在本地运行相同的嵌入模型来理解你的查询。无需云端调用;你的库永远不会离开你的机器。
功能
search_notes— 跨一个或多个库进行语义搜索。匹配整篇笔记以及单个章节(块),返回按相似度排序的结果及内容片段。get_similar_notes— 与给定笔记相似的笔记(已存储的嵌入)。get_connection_graph— 向外遍历相似度链接,绘制相关想法图谱。get_note_content— 读取笔记,或提取特定块。list_vaults/get_stats— 已加载内容、数量、模型、加载错误。
Related MCP server: ob-smart-connections-mcp
环境要求
Node.js 20+
一个安装了 Smart Connections 插件并已生成嵌入的 Obsidian 库(v2 已针对 Smart Connections 3.x 数据测试)
一个 MCP 客户端(Claude Desktop、Claude Code 等)
设置(Claude Desktop)
添加到 claude_desktop_config.json 并重启 Claude Desktop:
{
"mcpServers": {
"smart-connections": {
"command": "npx",
"args": ["-y", "smart-connections-mcp"],
"env": {
"SMART_VAULT_PATH": "/path/to/Vault One,/path/to/Vault Two"
}
}
}
}一个库或多个库——用逗号分隔路径。
SMART_VAULT_PATHS(复数形式)也可作为 SMART_VAULT_PATH 的别名,若两者同时设置,则优先使用前者。
Claude Code
claude mcp add smart-connections -e SMART_VAULT_PATH="/path/to/vault" -- npx -y smart-connections-mcp工作原理
Smart Connections 将每篇笔记和每个块的嵌入向量存储在 .smart-env/ 中。此服务器将这些向量加载到内存中,当你搜索时,使用你的库所用的相同模型嵌入你的查询(下载一次,约 25MB,通过 transformers.js 在本地运行)。结果按余弦相似度排序。你在 Obsidian 中所做的编辑会被自动捕获。
如果嵌入模型无法加载(例如首次运行时无网络),或某个库尚无嵌入,搜索将降级为字面关键词匹配,并明确说明("mode": "keyword-fallback" 以及一个指明原因的 warning)。当只有部分库降级时,mode 保持 "semantic",这些行带有 "match": "keyword",并且始终排在真正的语义行之后。
从 v1 迁移
已移除
get_embedding_neighbors。search_notes现在是真正的语义搜索,其响应包含vault、scope、block、snippet和mode字段。其余内容均向后兼容;单库
SMART_VAULT_PATH配置可原样使用。
开发
npm install
npm test # build + CI-tier tests (no network)
npm run test:live # + real-model tests (downloads ~25MB once)
npm run smoke -- "/path/to/vault" "your query"MIT — 参见 LICENSE。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Search your Obsidian vault to quickly find notes by title or keyword, summarize related content, a…
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Token-efficient MCP memory for Markdown vaults. Tiered search, GraphRAG, AI memories.
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables Claude to perform semantic search across your Obsidian vault using Smart Connections vector database. Provides meaning-based search, related note discovery, and context retrieval for RAG queries instead of basic keyword matching.10
- AlicenseNot gradedqualityFmaintenanceEnables AI agents to find semantic connections and perform text searches in Obsidian vaults using the Smart Connections plugin data.12414MIT
- AlicenseNot gradedqualityCmaintenanceEnables semantic search over an Obsidian vault using natural language, retrieving relevant notes and extracted conclusions.MIT
- AlicenseNot gradedqualityAmaintenanceEnables semantic search and retrieval over an Obsidian vault using local or API-based embeddings, allowing AI assistants to find notes by meaning, get related content, and pull context during conversations.15MIT
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/msdanyg/smart-connections-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server