LiveGraphRAG MCP Server
Provides version-aware retrieval and question answering over official Nextcloud documentation, enabling users to ask about configuration, upgrades, troubleshooting, and feature differences with cited sources.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@LiveGraphRAG MCP ServerExplain key differences between Nextcloud 32 and 33 with cited sources."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
LiveGraphRAG
把散落在产品文档里的答案,变成带来源、能追溯、可继续追问的知识服务。
LiveGraphRAG 是一个面向私有化软件运维支持场景的 GraphRAG 项目。它以 Nextcloud 31、32、33 的官方资料为知识底座:当用户询问配置、升级、排错或功能差异时,系统不仅给出回答,还会附上对应的原始文档片段、版本信息与引用来源。
项目围绕 RAG 与 Agentic RAG 工作流构建,既能作为知识检索服务接入业务系统,也能为智能助手提供可靠的上下文与引用。
它能做什么
根据问题检索不同版本的官方资料,避免把旧版本说明当成当前答案。
结合关键词、向量和图关系寻找相关信息,而不是只做简单的文本匹配。
返回可点击、可阅读的来源证据,让每条结论都能回到原文。
支持租户与版本隔离,适合模拟多环境知识库的使用方式。
提供受限 Agent 流程:先查证据,再组织答案,引用不通过就不输出。
通过 Redis 缓存、限流、异步索引与可观测性组件,模拟一套更接近真实服务的运行链路。
Related MCP server: OntoRamp Graph Query
项目一览
用户 / AI Client
│
▼
Web / API Client
│
▼
检索与问答服务
┌─────┼─────────┐
▼ ▼ ▼
PostgreSQL Redis Neo4j
文档与快照 缓存与任务 图关系
│
▼
模型 Provider(可切换)系统默认使用确定性 Provider,方便在没有模型凭证的情况下体验完整流程;需要真实模型时,可以通过环境变量显式切换。
快速开始
环境要求
Docker 与 Docker Compose
Python 3.12+
GNU Make(Windows 可使用兼容环境)
启动服务
cp .env.example .env
make up
make migrate
make import-postgres
make demo-up.env 只用于本地配置,不应提交任何密钥或真实环境信息。
体验演示页面
启动演示页面:
make demo-ui然后访问 http://127.0.0.1:8080。页面提供两种使用方式:
证据检索:输入问题,直接查看相关文档、版本与来源卡片。
Agent 分析:观看系统依次检索资料、整理信息并生成带引用回答的过程。
如需启用 DeepSeek,在本机 .env 中设置 DEEPSEEK_API_KEY,并在启动前设置:
LIVEGRAPHRAG_LLM_PROVIDER=deepseek真实模型调用可能产生费用。
产品界面
下列截图展示从提出运维问题、检索版本化资料,到生成可验证回答并回溯原文证据的完整链路。
首页与能力概览 | 提问与版本选择 |
|
|
可验证回答 | 来源证据库 |
|
|
技术组成
领域 | 主要组件 |
服务接口 | Python、FastAPI、SSE |
关系与检索 | PostgreSQL、pgvector、全文检索、Neo4j |
异步处理 | PostgreSQL Outbox、Redis Streams |
缓存与限流 | Redis、Lua Token Bucket、SingleFlight |
可观测性 | OpenTelemetry、Prometheus、Grafana |
容器化 | Docker Compose |
项目结构
apps/ API、智能检索与 Worker 入口
livegraphrag/ 领域模型、应用服务与基础设施实现
migrations/ PostgreSQL 迁移
data/ 固定语料、清单与评测数据
tests/ 单元、契约与集成测试
docs/ 架构、实验记录与运行说明
scripts/ 数据处理与本地工具脚本延伸阅读
数据说明
仓库中的资料来自公开的 Nextcloud 官方文档。示例租户、角色和使用场景均为合成数据,不包含真实用户或企业信息。
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
Versioned documentation registry and semantic search for AI tools and coding assistants.
Governed, auditable knowledge your team curates for its AI assistants, self-hostable
Your company's brain for AI agents. Cited, permission-aware knowledge across every system.
Ingest, manage, and retrieve documents for RAG-powered AI applications
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to crawl, index, and retrieve information from technical documentation using semantic search, with optional knowledge graph validation for code hallucination detection.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to query organizational architecture and governance constraints, returning evidence-grounded answers from documented structures.MIT
- AlicenseAqualityAmaintenanceEnables teams to capture and distill knowledge from sessions, meetings, and feeds into a searchable, vector-embedded graph, then retrieve or synthesize it conversationally via semantic search and citations.1724Apache 2.0
- FlicenseAqualityAmaintenanceEnables version-aware retrieval over the Neutrinos documentation corpus using hybrid BM25/dense search, reranking, and link-graph expansion to answer queries accurately for the user's specific product version.6
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/Sylvia145/LiveGraphRAG'
If you have feedback or need assistance with the MCP directory API, please join our Discord server



