RagDocs MCP Server
RagDocs MCP 服务器
模型上下文协议 (MCP) 服务器,使用 Qdrant 向量数据库和 Ollama/OpenAI 嵌入提供 RAG(检索增强生成)功能。该服务器通过向量相似性实现文档的语义搜索和管理。
特征
添加带有元数据的文档
通过文档进行语义搜索
列出并组织文档
删除文档
支持 Ollama(免费)和 OpenAI(付费)嵌入
自动文本分块和嵌入生成
使用 Qdrant 进行矢量存储
Related MCP server: Qdrant Retrieve MCP Server
先决条件
Node.js 16 或更高版本
以下 Qdrant 设置之一:
使用 Docker 的本地实例(免费)
带有 API 密钥的 Qdrant Cloud 帐户(托管服务)
以下其中之一用于嵌入:
Ollama 在本地运行(默认,免费)
OpenAI API 密钥(可选,付费)
可用工具
1. 添加文档
向 RAG 系统添加文档。
参数:
url(必填):文档 URL/标识符content(必填):文档内容metadata(可选):文档元数据title:文档标题contentType:内容类型(例如“text/markdown”)
2. 搜索文档
使用语义相似性搜索存储的文档。
参数:
query(必需):自然语言搜索查询options(可选):limit:最大结果数(1-20,默认值:5)scoreThreshold:最小相似度得分(0-1,默认值:0.7)filters:domain:按域过滤hasCode:过滤包含代码的文档after:过滤日期之后的文档(ISO 格式)before:过滤日期之前的文档(ISO 格式)
3. 列出文档
列出所有存储的文档,并提供分页和分组选项。
参数(全部可选):
page:页码(默认值:1)pageSize:每页文档数(1-100,默认值:20)groupByDomain:按域分组文档(默认值:false)sortBy:排序字段(“时间戳”、“标题”或“域”)sortOrder:排序顺序(“asc”或“desc”)
4. 删除文档
从 RAG 系统中删除文档。
参数:
url(必填):要删除的文档的 URL
安装
npm install -g @mcpservers/ragdocsMCP 服务器配置
{
"mcpServers": {
"ragdocs": {
"command": "node",
"args": ["@mcpservers/ragdocs"],
"env": {
"QDRANT_URL": "http://127.0.0.1:6333",
"EMBEDDING_PROVIDER": "ollama"
}
}
}
}使用 Qdrant Cloud:
{
"mcpServers": {
"ragdocs": {
"command": "node",
"args": ["@mcpservers/ragdocs"],
"env": {
"QDRANT_URL": "https://your-cluster-url.qdrant.tech",
"QDRANT_API_KEY": "your-qdrant-api-key",
"EMBEDDING_PROVIDER": "ollama"
}
}
}
}使用 OpenAI:
{
"mcpServers": {
"ragdocs": {
"command": "node",
"args": ["@mcpservers/ragdocs"],
"env": {
"QDRANT_URL": "http://127.0.0.1:6333",
"EMBEDDING_PROVIDER": "openai",
"OPENAI_API_KEY": "your-api-key"
}
}
}
}使用 Docker 的本地 Qdrant
docker run -d --name qdrant -p 6333:6333 -p 6334:6334 qdrant/qdrant环境变量
QDRANT_URL:您的 Qdrant 实例的 URL对于本地:“ http://127.0.0.1:6333 ”(默认)
QDRANT_API_KEY:Qdrant Cloud 的 API 密钥(使用云实例时需要)EMBEDDING_PROVIDER:嵌入提供商的选择(“ollama”或“openai”,默认值:“ollama”)OPENAI_API_KEY:OpenAI API 密钥(如果使用 OpenAI,则需要)EMBEDDING_MODEL:用于嵌入的模型对于 Ollama:默认为“nomic-embed-text”
对于 OpenAI:默认为“text-embedding-3-small”
执照
Apache 许可证 2.0
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
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
Ingest, manage, and retrieve documents for RAG-powered AI applications
Versioned documentation registry and semantic search for AI tools and coding assistants.
The Needle MCP server enables semantic search on documents stored in files like PDFs, DOCX, and XLSX by connecting AI applications to external data sources. It provides capabilities to create and manage document collections, perform natural language searches on stored content, and retrieve relevant information without requiring exact keyword matches.
Search your knowledge bases from any AI assistant using hybrid RAG.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceFacilitates knowledge graph representation with semantic search using Qdrant, supporting OpenAI embeddings for semantic similarity and robust HTTPS integration with file-based graph persistence.3324MIT
- AlicenseNot gradedqualityDmaintenanceEnables semantic search across multiple Qdrant vector database collections, supporting multi-query capability and providing semantically relevant document retrieval with configurable result counts.46MIT
- FlicenseNot gradedqualityDmaintenanceThis server enables semantic search capabilities using Qdrant vector database and OpenAI embeddings, allowing users to query collections, list available collections, and view collection information.7-

Agentsetofficial
AlicenseAqualityCmaintenanceAn open-source platform for Retrieval-Augmented Generation (RAG). Upload documents and query them ⚡12631MIT
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/heltonteixeira/ragdocs'
If you have feedback or need assistance with the MCP directory API, please join our Discord server