OSF MCP Server

OSF MCP Server

An MCP server for interacting with the Open Science Framework (OSF), enabling search for projects, registrations, preprints, and file management.

Category
访问服务器

README

OSF MCP Server

An MCP (Model Context Protocol) server for interacting with the Open Science Framework (OSF). Search projects, registrations, preprints, manage files, and more.

Features

  • Search OSF Content

    • Projects (public and private with authentication)
    • Registrations (pre-registered studies)
    • Preprints (from OSF Preprints and partner services)
  • File Management

    • List project files
    • Download files with PDF-to-Markdown conversion
    • Read cached file content
  • Project Management (requires authentication)

    • Create new projects
    • Update project metadata
    • Access wiki content
  • DOI Resolution

    • Resolve OSF DOIs to resources

Installation

# Clone the repository
cd tools/osf-mcp-server

# Create virtual environment
uv venv
source .venv/bin/activate

# Install with dependencies
uv pip install -e ".[test]"

Configuration

Environment Variables

Variable Description Default
OSF_TOKEN Personal Access Token for authenticated access None (public only)
OSF_STORAGE_PATH Path for downloaded files ~/.osf-mcp-server/files
OSF_MAX_RESULTS Maximum search results 50
OSF_REQUEST_TIMEOUT API timeout in seconds 60

Getting an OSF Token

  1. Log in to osf.io
  2. Go to Settings → Personal Access Tokens
  3. Create a new token with required scopes
  4. Set OSF_TOKEN environment variable
export OSF_TOKEN="your_token_here"

Usage

Running the Server

# Run directly
python -m osf_mcp_server

# Or via entry point
osf-mcp-server

# With custom storage path
osf-mcp-server --storage-path /path/to/storage

Claude Desktop Integration

Add to your Claude Desktop config (claude_desktop_config.json):

{
  "mcpServers": {
    "osf": {
      "command": "python",
      "args": ["-m", "osf_mcp_server"],
      "env": {
        "OSF_TOKEN": "your_token_here"
      }
    }
  }
}

Or with uv:

{
  "mcpServers": {
    "osf": {
      "command": "uv",
      "args": [
        "--directory", "/path/to/osf-mcp-server",
        "run", "osf-mcp-server"
      ],
      "env": {
        "OSF_TOKEN": "your_token_here"
      }
    }
  }
}

Available Tools

Search Tools

Tool Description
search_projects Search for OSF projects by title, tags, category
search_registrations Search for pre-registered studies
search_preprints Search for preprints from OSF and partner services

Project Tools

Tool Description
get_project Get detailed project information
create_project Create a new project (auth required)
update_project Update project metadata (auth required)

File Tools

Tool Description
list_files List files and folders in a project
download_file Download and cache a file locally
read_file Read content of a downloaded file

Other Tools

Tool Description
get_wiki List or get wiki page content
resolve_doi Resolve an OSF DOI to a resource

Examples

Search for Psychology Projects

Search for projects related to "cognitive bias":
- query: "cognitive bias"
- tags: ["psychology"]
- max_results: 20

Download a Research Paper

1. Search for preprints: query="machine learning"
2. List project files: project_id="abc12"
3. Download PDF: file_id="xyz789"
4. Read content: file_id="xyz789"

Create a New Project

Create project:
- title: "My Research Project"
- description: "A study on..."
- public: false
- tags: ["experiment", "2024"]

Development

Running Tests

# Run all tests
python -m pytest

# Run with coverage
python -m pytest --cov=osf_mcp_server

# Run specific test file
python -m pytest tests/test_search.py -v

Code Formatting

# Format with black
black src/

# Lint with ruff
ruff check src/

Architecture

osf-mcp-server/
├── src/osf_mcp_server/
│   ├── __init__.py          # Entry point
│   ├── server.py             # MCP server implementation
│   ├── config.py             # Configuration settings
│   ├── osf_client.py         # OSF API client
│   ├── tools/                # MCP tools
│   │   ├── search_*.py       # Search tools
│   │   ├── *_file.py         # File tools
│   │   └── ...
│   ├── resources/            # Resource management
│   │   └── osf_manager.py
│   └── prompts/              # Research prompts
│       └── research_prompts.py
└── tests/

OSF API Reference

This server uses the OSF API v2. Key endpoints:

  • /nodes/ - Projects and components
  • /registrations/ - Pre-registered studies
  • /preprints/ - Preprints
  • /files/ - File operations
  • /wikis/ - Wiki pages

License

MIT License

Contributing

Contributions welcome! Please:

  1. Fork the repository
  2. Create a feature branch
  3. Add tests for new functionality
  4. Submit a pull request

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选