PaperMCP
A lightweight, local, multi-project isolated paper index server that provides dual retrieval (BM25 + dense vector) via MCP, enabling agents to search and manage paper collections across isolated projects.
README
PaperMCP
一个轻量、单机、多项目隔离、可被任意通用 Agent 通过 MCP 调用的 论文双路检索索引服务。
定位
- 每个用户/团队可创建多个 Project，每个 Project 独立数据源 + 独立索引 + 独立鉴权。
- 支持 PDF / Markdown / LaTeX / DOCX 四种格式，一次性上传，自动解析、切块、建索引。
- 双路检索：BM25（字面/术语/公式）+ bge-m3 稠密向量，用 RRF 融合， 再乘 文档权重 得到最终排序。
- 双入口：
- MCP Server — 面向 Agent（Claude / CodeBuddy / ...），启动时绑定 project，长会话免密。
- Admin HTTP Server — 面向人，含项目 CRUD、文档 CRUD、统计、审计、渲染查看。
架构
快速开始（v0.1 正在开发中）
# 1. 安装
pip install -e ".[dev]"
# 2. 配置
cp .env.example .env
# 编辑 .env，设置 INVITE_CODES / JWT_SECRET
# 3. 启动 Admin，创建首个项目
paper-mcp serve admin
# 浏览器打开 http://localhost:8765，用邀请码建项目
# 4. 挂到 Agent（示例：CodeBuddy MCP 配置）
# {
# "papermcp-<project>": {
# "command": "paper-mcp",
# "args": ["serve", "mcp", "--project", "<project-name>"],
# "env": {
# "PAPER_MCP_USERNAME": "...",
# "PAPER_MCP_PASSWORD": "..."
# }
# }
# }
CLI 也提供短别名 pmcp，等价于 paper-mcp。
项目状态
- [x] 架构文档冻结（v3）
- [x] v0.1 骨架代码
- [x] v0.1 后端完整实现（config / domain / infra / core / service / server / cli）
- [ ] v0.1 端到端联调 + 打包
- [ ] v0.2 管理端 UI + FAISS 增量重建
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.