JCR Partition MCP Server

Simplified Chinese | English

A Model Context Protocol (MCP) server based on ShowJCR repository data, providing Large Language Models with the latest journal partition table query capabilities.

Features

🔧 Tools

• search_journal - Search for journal information, including impact factors, partitions, warning status, etc.

• get_partition_trends - Get trend analysis of journal partition changes

• check_warning_journals - Query international journal warning lists

• compare_journals - Compare comprehensive information across multiple journals

📋 Resources

• jcr://database-info - Basic database information and statistics

💡 Prompts

• journal_analysis_prompt - Dedicated prompt template for journal analysis

Related MCP server: University Rankings MCP Server

Data Sources

This project is based on data from the ShowJCR repository, including:

• Cutting-edge Journal Partition Table (2026 edition, 22,299 journals + 15 important computer science conferences; starting from this edition, warning information is embedded as "Warning Tag: Under Review")

• CAS Partition Table Upgraded Version (2025, 2023, 2022)

• JCR Journal Impact Factors (2024, 2023, 2022)

• International Journal Warning Lists (2025, 2024, 2023, 2021, 2020; no longer released separately upstream starting from 2026)

• CCF Recommended International Academic Conferences and Journals Directory (2026, 2022)

• High-quality Scientific Journal Classification Directory in Computing (2025, 2022)

2026 Version Note: The check_warning_journals tool scans both the traditional GJQKYJMD* warning tables and the XR2026.WarningTag field, covering both old and new warning sources.

Installation and Deployment

1. Environment Requirements

• Python 3.10+ (Hard requirement for mcp SDK)

• SQLite3 (Usually built-in with Python)

2. Install Dependencies

pip install -r requirements.txt

3. Data Synchronization

Data must be synchronized before the first run:

python data_sync.py

Select "1" to synchronize all data and wait for the download and import to complete.

4. Start the Server

python jcr_mcp_server.py

Client Testing

Independent Testing

python test_client.py

Select mode:

• Mode 1: Automatically test all functions

• Mode 2: Interactive query mode

Claude Desktop Integration

Add to the Claude Desktop configuration file (%APPDATA%\Claude\claude_desktop_config.json or ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "jcr-partition": {
      "command": "/path/to/python",
      "args": ["/path/to/jcr_mcp_server.py"],
      "cwd": "/path/to/project"
    }
  }
}

The claude_desktop_config.json in the repository can be used as a reference template.

Claude Code Integration

Register with one line via CLI (scope user means globally available):

claude mcp add -s user jcr-partition -- /path/to/python /path/to/jcr_mcp_server.py

After registration, you can confirm the status via claude mcp list, which should show ✓ Connected.

Usage Examples

1. Journal Search

# 搜索Nature期刊
result = await session.call_tool("search_journal", {
    "journal_name": "Nature"
})

2. Partition Trend Analysis

# 获取Science期刊分区变化趋势
result = await session.call_tool("get_partition_trends", {
    "journal_name": "Science"
})

3. Journal Comparison

# 对比三个顶级期刊
result = await session.call_tool("compare_journals", {
    "journal_list": "Nature,Science,Cell"
})

4. Warning Journal Query

# 查询预警期刊
result = await session.call_tool("check_warning_journals", {
    "keywords": "MDPI"
})

Output Examples

Journal Search Results

📚 期刊名称: NATURE

【2024年】（JCR）
  📊 影响因子: 48.5
  🏆 分区: Q1
  📖 学科类别: MULTIDISCIPLINARY SCIENCES(SCIE)

【2025年】（中科院升级版）
  🏆 分区: 1 [1/118]（Top）
  📖 学科类别: 综合性期刊

【2026年】（新锐期刊分区表）
  🏆 分区: 1 区（Top）
  📖 学科类别: 综合性期刊

Journal Comparison Results

📊 期刊对比分析结果

期刊名称                    最新影响因子      最新分区        预警状态       
----------------------------------------
Nature                    64.8           Q1             正常          
Science                   56.9           Q1             正常          
Cell                      64.5           Q1             正常          

💡 投稿建议:
  ⭐ Nature: 顶级期刊，强烈推荐
  ⭐ Science: 顶级期刊，强烈推荐  
  ⭐ Cell: 顶级期刊，强烈推荐

Technical Architecture

Data Layer

• SQLite database stores all partition table data

• Supports historical data for multiple years

• Automatic data synchronization and verification mechanism

Service Layer

• FastMCP framework builds the MCP server

• Asynchronous processing improves performance

• Comprehensive error handling and logging

Interface Layer

• Standard MCP protocol interface

• Supports three types: tools, resources, and prompts

• Compatible with various MCP clients

Extension Instructions

Adding New Data Sources

1. Add the new data source to the data_sources dictionary in data_sync.py

2. Run data synchronization to update the database

3. Update the parsing logic in jcr_mcp_server.py

Adding New Tools

1. Use the @app.tool() decorator in jcr_mcp_server.py

2. Implement the specific query logic

3. Add appropriate docstrings

Deploying to the Cloud

You can deploy the server to a cloud platform, supporting HTTP transport:

app.run(transport="streamable-http", host="0.0.0.0", port=8080)

Related Links

• ShowJCR Original Project

• MCP Official Documentation

• Claude Desktop MCP Integration Guide

License

This project is open-sourced under the MIT license.

Contribution

Feel free to submit Issues and Pull Requests to improve this project!