Vector Search — In-Memory TF-IDF Semantic Store MCP配置与使用教程
io.smithery.axel-belfort.vector-search · vlatest
In-memory vector search API for AI agents. Store documents and query by semantic meaning using TF-IDF vectorization with cosine similarity. Lightweight alternative to Pinecone/Weaviate for small datasets. Tools: data_vector_search. Use this for building simple RAG systems, document matching, or semantic search over small collections (< 10K docs). IMPORTANT: For web-wide search, use web_search_query instead. Returns: {results[], scores[], matchCount}. No API key required — x402 micropayment $0.005/call on Base L2.
建议先在本页复制安装配置，再到上游核对文档与权限。
热度数据
产品介绍
In-memory vector search API for AI agents. Store documents and query by semantic meaning using TF-IDF vectorization with cosine similarity. Lightweight alternative to Pinecone/Weaviate for small datasets. Tools: data_vector_search. Use this for building simple RAG systems, document matching, or semantic search over small collections (< 10K docs). IMPORTANT: For web-wide search, use web_search_query instead. Returns: {results[], scores[], matchCount}. No API key required — x402 micropayment $0.005/call on Base L2. Vector Search — In-Memory TF-IDF Semantic Store 是一个MCP Server，收录自 smithery。支持 streamable-http 传输。本页提供产品介绍、配置教程、安装命令与适用场景，可复制到 Cursor、Claude Code、VS Code。
MCP 实战教程：从安装到看见效果
按完整实例走一遍（含期望效果与对比验收）。装完本页资源后，用教程里的提示词核对是否真正生效。
安全与质量评测A+ 级 · 零权限本地沙盒
该工具经 AgentHub 静态安全特征扫描，无高危越权行为。建议在项目级配置文件中指定工作区范围。
需连接外部 API 或远程服务器，通信受客户端网络安全策略监管。
按平台快速复制
选择你的平台查看安装方式
- 打开项目根目录下的 .cursor/mcp.json（没有就新建）
- 点击「复制配置」粘贴进去；若已有其他 MCP，只合并 mcpServers 里的本条目
- 保存后按 Cmd+Shift+P（Windows：Ctrl+Shift+P）→ 输入 Reload Window 并执行
{
"mcpServers": {
"io-smithery-axel-belfort-vector-search": {
"url": "https://smithery.ai/servers/axel-belfort/vector-search"
}
}
}
