boop-mcp-rag
Boop MCP–RAG
Boop MCP–RAG 是一个与数据源无关的基础框架,为未来的检索增强生成(RAG)与模型上下文协议(MCP)系统提供结构基础。它在不模型提供方、数据源、凭据、数据库、向量数据库、远程 MCP 服务器或生产环境身份服务的前提下,实现了稳定的契约和确定性的本地参考路径。
该项目刻意定位为结构基础。它不是生产级 RAG 服务、自主智能体、API 网关、向量检索集群或远程工具执行器。
运行时拓扑
Consumer / MCP client
|
v
ContextRouter
| |
v v
QueryRetriever MCPHost
| |
v v
ContextDocument ToolResult
\ /
v v
ContextPayload提供方,检索存储、会话持久化、工具传输和遥测导出均在安装时通过接口选配。
边界 | 契约 | 本地参考路由适配器 | 安装时扩展点 |
数据引入 |
| 内存中的确定性分词切分 | 文档解析器、嵌入模型、索引器 |
检索 |
| 关键词重叠排序 | pgvector、Qdrung、混合搜索 |
会话状态 |
| 进程内存 | Redis、PostgreSQL |
工具 |
| 进程内 Pydantic 验证主机 | MCP STDIO、HTTP/SSE、gRPC 桥接 |
遥测 | OpenTelemetry API 跨度 | 仅 API 采集插桩 | OTLP 采集器/导出器 |
入口 | 占位符配置 | 配置项、无 | 认证、授权、限流适配器 |
Related MCP server: DocAgent-MCP
行为
ContextRouter 验证请求、获取上下文并发现已注册的工具;仅当调用方显式提供 requested_tool 时才执行工具。它在标准化的 ContextPayload 中组合用户配置、检索到的文档、工具定义、会话元数据以及可选调用结果。
参考知识适配器是确定性的关键词匹配,仅用于验证契约之时,并非用于声称提供语义/语义向量检索能力。本机 MCP 主机在执行处理器之前用 Pydantic 校验每个工具输入。
安装与验证
python3 -m pip install -e .
python3 -m unittest discover -s tests -p "test_*.py" -v
python3 -m compileall -q src tests server.py
boop-mcp-rag status本地 MCP 服务
启动本地 MCP 服务器:
mcp run server.py工具 | 用途 |
| 声明所安装的本地适配器和尚未安装的扩展点。 |
| 将调用方提供的文本记录到进程内存,不抓取外部内容。 |
| 检索上下文,并可选地执行正式请求的本地工具。 |
| 列出与传输层无关的工具描述符。 |
安装边界
应根据已验证的目标运行时、数据源、访问边界和运维要求,仅在此之后拷贝配置文件副本并选择真实的实现,避免本仓库包含任何密钥、机密字段、数据源转储或生产连接字符串。
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
- AlicenseBqualityAmaintenanceLocal end-to-end RAG system for agentic code editors, exposing retrieval-augmented generation via MCP to any compatible client.331MIT
- FlicenseNot gradedqualityCmaintenanceEnables local document question-answering and retrieval via MCP, supporting multi-turn conversation, intent recognition, and tools for document search, Q&A, and summarization.5
- FlicenseNot gradedqualityCmaintenanceEnables tool-calling over TCP for a local RAG pipeline, allowing document ingestion and querying via MCP tools, fully offline with no cloud dependencies.
- AlicenseNot gradedqualityAmaintenanceA local-first RAG engine that ingests documents (PDF, Markdown, images, etc.) and provides hybrid search, reranking, and LLM answer synthesis via MCP for AI agent integration.1MIT
Related MCP Connectors
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.
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/ttacleinad-boop/MCP---RAG'
If you have feedback or need assistance with the MCP directory API, please join our Discord server