Metadata-Version: 2.4
Name: research-automation-mcp-server
Version: 0.1.0
Summary: MCP server for autonomous research automation: web search, Wikipedia, arXiv, Crossref, fact-checking and report compilation
Project-URL: Homepage, https://github.com/AiAgentKarl/research-automation-mcp-server
Project-URL: Repository, https://github.com/AiAgentKarl/research-automation-mcp-server
Author: AiAgentKarl
License: MIT
Keywords: academic,ai-agent,arxiv,automation,duckduckgo,fact-check,mcp,model-context-protocol,research,wikipedia
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Internet :: WWW/HTTP :: Indexing/Search
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Requires-Dist: duckduckgo-search>=6.0.0
Requires-Dist: feedparser>=6.0.0
Requires-Dist: httpx>=0.27.0
Requires-Dist: mcp[cli]>=1.0.0
Description-Content-Type: text/markdown

# research-automation-mcp-server

[![PyPI version](https://badge.fury.io/py/research-automation-mcp-server.svg)](https://pypi.org/project/research-automation-mcp-server/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
[![MCP](https://img.shields.io/badge/MCP-compatible-green.svg)](https://modelcontextprotocol.io)

MCP server for autonomous research automation. Search the web, Wikipedia, arXiv and Crossref — all in one tool, no API keys required.

## Tools (11 total)

| Tool | Description | Source |
|------|-------------|--------|
| `search_web` | Web search via DuckDuckGo | DuckDuckGo |
| `search_news` | Current news search | DuckDuckGo News |
| `wikipedia_search` | Find Wikipedia articles | Wikipedia API |
| `wikipedia_summary` | Get article summary | Wikipedia REST API |
| `arxiv_search` | Search academic papers | arXiv.org |
| `arxiv_get_paper` | Get paper details by ID | arXiv.org |
| `crossref_search` | Search 150M+ publications | Crossref API |
| `crossref_get_paper` | Get paper by DOI | Crossref API |
| `research_topic` | Multi-source research | All sources |
| `compile_report` | Generate research report | — |
| `fact_check` | Verify claims | Web + Wikipedia |

## Installation

```bash
pip install research-automation-mcp-server
```

## Usage with Claude Desktop

Add to your `claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "research-automation": {
      "command": "research-automation-mcp-server"
    }
  }
}
```

## Example Queries

- "Research the latest developments in quantum computing"
- "Find arXiv papers about large language models published in 2024"
- "Fact-check: Does coffee cause cancer?"
- "Search Wikipedia for 'CRISPR gene editing' and give me a summary"
- "Find academic papers about climate change via Crossref"

## Features

- **No API keys required** — all sources are free and open
- **Multi-source** — combines web, encyclopedia and academic sources
- **Research automation** — `research_topic` queries all sources in parallel
- **Fact-checking** — cross-reference claims across multiple sources
- **Academic focus** — arXiv (preprints) + Crossref (150M+ published papers)

## License

MIT
