RAG MCP server
RAG-MCP服务器
使用模型控制协议 (MCP) 的通用检索增强生成 (RAG) 服务器,旨在使用 RISC Zero 的 Bonsai 文档进行测试。
概述
该项目实现了一个 RAG 服务器,它:
使用 MCP(模型控制协议)进行标准化通信
实现用于文档查询的 RAG(检索增强生成)工作流程
可以使用 RISC Zero 的 Bonsai 文档进行测试
通过 Ollama 支持本地 LLM 集成
Related MCP server: linkup-mcp
特征
文档提取和索引
语义搜索功能
本地法学硕士整合
MCP 协议合规性
RISC Zero Bonsai 文档支持
先决条件
Python 3.12+
Ollama(用于本地法学硕士支持)
诗歌(用于依赖管理)
安装
安装 Python 依赖项:
poetry install安装并启动 Ollama:
# Install Ollama
brew install ollama # for macOS
# or
curl -fsSL https://ollama.com/install.sh | sh # for Linux
# Start Ollama service
ollama serve拉取所需模型:
ollama pull llama2用法
启动 MCP 服务器:
poetry run python mcp_server.py服务器将:
初始化 LLM 和嵌入模型
从数据目录提取文档
使用 RAG 工作流处理查询
使用 RISC Zero Bonsai 文档进行测试:
将 RISC Zero Bonsai 文档放在
data/目录中向服务器查询 Bonsai 的功能和实现
项目结构
mcp_server.py:主服务器实现rag.py:RAG 工作流程实现data/:文档提取目录storage/:向量存储和文档存储start_ollama.sh:启动 Ollama 服务的脚本
使用 RISC Zero Bonsai 进行测试
该服务器已配置为与 RISC Zero 的 Bonsai 文档配合使用。您可以:
将 Bonsai 文档添加到
data/目录询问 Bonsai 的功能、实现细节和使用方法
使用 Bonsai 特定问题测试 RAG 工作流程
由proofofsid用 ❤️ 制作
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 Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI coding assistants to search and retrieve information from a locally ingested knowledge base using hybrid search, grounded in user-curated documentation.17MIT
- FlicenseNot gradedqualityBmaintenanceProvides web search and local document RAG using Ollama, enabling privacy-preserving AI assistance in Cursor IDE.
- FlicenseNot gradedqualityDmaintenanceEnables semantic code search across codebases using AI embeddings and vector similarity, integrated with Claude Desktop and Cursor.
- FlicenseNot gradedqualityDmaintenanceStores and searches AI-generated knowledge about software projects, enabling Cursor to access project structures, design patterns, best practices, and technical documentation.
Related MCP Connectors
Search your knowledge bases from any AI assistant using hybrid RAG.
A personal RAG database you build from chat, so AI creates work that sounds like you.
Governed, auditable knowledge your team curates for its AI assistants, self-hostable
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/proofofsid/rag-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server