All-in-MCP
Enables academic research through paper search across multiple databases (IACR, CryptoBib, Crossref, Google Scholar), PDF processing, and GitHub repository browsing. Features modular architecture with FastMCP-based proxy server routing to specialized academic tools.
README
All-in-MCP
A FastMCP-based Model Context Protocol (MCP) server providing academic paper search, web search, and PDF processing utilities. Features a modular architecture with both proxy and standalone server capabilities.
<details> <summary>APaper Module Introduction</summary>

</details>
Architecture
All-in-MCP uses a modern FastMCP architecture with three main components:
- 🔄 All-in-MCP Proxy Server: Main server that routes requests to academic tools and web search
- 📚 APaper Module: Isolated academic research server with specialized paper search tools
- 🔍 Qwen Search Module: Web search server powered by Qwen/Dashscope API with SSE-based MCP
This design provides better modularity, performance, and scalability.
Features
All servers expose search tools as FastMCP endpoints with automatic tool registration:
Available Tools
| Category | Tool Name | Description | Backend |
|---|---|---|---|
| Academic Research | apaper_search_iacr_papers |
Search academic papers from IACR ePrint Archive | APaper |
apaper_download_iacr_paper |
Download PDF of an IACR ePrint paper | APaper | |
apaper_read_iacr_paper |
Read and extract text content from an IACR ePrint paper PDF | APaper | |
| Bibliography Search | apaper_search_dblp_papers |
Search DBLP computer science bibliography database | APaper |
| Cross-platform Search | apaper_search_google_scholar_papers |
Search academic papers across disciplines with citation data | APaper |
| Web Search | qwen_search_web_search |
Search the web using Qwen/Dashscope API | Qwen Search |
| GitHub Repository | github-repo-mcp_getRepoAllDirectories |
Get all directories from a GitHub repository | GitHub-Repo-MCP |
github-repo-mcp_getRepoDirectories |
Get directories from a specific path in GitHub repository | GitHub-Repo-MCP | |
github-repo-mcp_getRepoFile |
Get file content from GitHub repository | GitHub-Repo-MCP |
All tools are implemented using FastMCP decorators with automatic registration, built-in validation, and enhanced error handling.
Quick Start
Prerequisites
- Python 3.10 or higher
pipxfor Python package installationnpxfor MCP Inspector (Node.js required)
Integration with MCP Clients
Add the servers to your MCP client configuration:
VSCode Configuration (.vscode/mcp.json)
{
"servers": {
"all-in-mcp": {
"type": "stdio",
"command": "pipx",
"args": ["run", "all-in-mcp"],
"env": {
"APAPER": "true",
"QWEN_SEARCH": "true",
"DASHSCOPE_API_KEY": "your_api_key_here",
"GITHUB_REPO_MCP": "true"
}
}
}
}
Claude Code Configuration (.mcp.json)
{
"mcpServers": {
"all-in-mcp": {
"type": "stdio",
"command": "pipx",
"args": ["run", "all-in-mcp"],
"env": {
"APAPER": "true",
"QWEN_SEARCH": "true",
"DASHSCOPE_API_KEY": "your_api_key_here",
"GITHUB_REPO_MCP": "true"
}
}
}
}
Server Options
The main proxy server supports multiple MCP backends through environment variables:
# Run with APaper academic tools enabled
APAPER=true pipx run all-in-mcp
# Run with Qwen Search web search enabled
QWEN_SEARCH=true DASHSCOPE_API_KEY=your_api_key_here pipx run all-in-mcp
# Run with GitHub repository tools enabled
GITHUB_REPO_MCP=true pipx run all-in-mcp
# Run with all backends enabled
APAPER=true QWEN_SEARCH=true DASHSCOPE_API_KEY=your_api_key_here GITHUB_REPO_MCP=true pipx run all-in-mcp
# Run standalone APaper server (academic tools only)
pipx run apaper
# Run standalone Qwen Search server (web search only)
DASHSCOPE_API_KEY=your_api_key_here pipx run qwen-search
Note: If you have the package installed globally, you can also run directly:
all-in-mcporqwen-search
Debugging & Testing
MCP Inspector
Use the official MCP Inspector to debug and test server functionality:
# Debug the main proxy server with APaper tools
APAPER=true npx @modelcontextprotocol/inspector pipx run all-in-mcp
# Debug with all backends enabled
APAPER=true GITHUB_REPO_MCP=true npx @modelcontextprotocol/inspector pipx run all-in-mcp
# Debug standalone APaper server
npx @modelcontextprotocol/inspector pipx run apaper
Local Development with uv
When developing locally, use uv run to debug specific MCP functions:
# Debug APaper server (academic tools)
npx @modelcontextprotocol/inspector uv run apaper
# Debug all-in-mcp proxy with APaper enabled
APAPER=true npx @modelcontextprotocol/inspector uv run all-in-mcp
# Debug all-in-mcp proxy with GitHub repo tools enabled
GITHUB_REPO_MCP=true npx @modelcontextprotocol/inspector uv run all-in-mcp
# Debug all-in-mcp with all backends enabled
APAPER=true QWEN_SEARCH=true DASHSCOPE_API_KEY=your_api_key_here GITHUB_REPO_MCP=true npx @modelcontextprotocol/inspector uv run all-in-mcp
# Debug Qwen Search server
DASHSCOPE_API_KEY=your_api_key_here npx @modelcontextprotocol/inspector uv run qwen-search
The MCP Inspector provides:
- 🔍 Interactive Tool Testing: Test all available tools with real parameters
- 📊 Server Information: View server capabilities and tool schemas
- 🐛 Debug Messages: Monitor server communication and error messages
- ⚡ Real-time Testing: Execute tools and see results immediately
Perfect for development, debugging, and understanding how the FastMCP tools work.
<details> <summary>Development</summary>
For development setup and contribution guidelines, see the Development Guide.
Quick Development Setup
# Clone the repository
git clone https://github.com/jiahaoxiang2000/all-in-mcp.git
cd all-in-mcp
# Install with development dependencies
uv sync --extra dev
# Run tests (now using unittest)
uv run python tests/test_fastmcp_server.py
uv run python tests/test_apaper_iacr.py
uv run python tests/test_apaper_pdf.py
uv run python tests/test_qwen_search.py
</details>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。