SPSS-MCP

A Model Context Protocol (MCP) server that gives AI assistants direct access to IBM SPSS Statistics for statistical analysis.

Describe your analysis in plain language — SPSS-MCP translates it into SPSS syntax, runs it against the real SPSS engine, and returns Markdown-formatted results.

🚀 快速开始： 查看 QUICK_START.md 或直接运行 install.bat 一键安装

Presentation Page

配套网页主题：Claude Code 与 SPSS-MCP：从概念到一键配置

适合培训、汇报和课堂演示，内容覆盖：

• 什么是 Claude Code，以及它和网页对话式协作的区别
• 什么是 MCP 协议
• Claude Code 的安装与配置
• GLM key 获取
• SPSS-MCP 的安装、配置与一键接入
• 简单统计分析示例与现场演示路径

Contact

• 公众号：人类变量
• 微信：Exekiel179

Requirements

• Windows 10/11
• Python 3.10+
• IBM SPSS Statistics (version 20-31)
• Claude Code with MCP support

Quick Install

One-Click (Recommended)

git clone https://github.com/Exekiel179/SPSS-MCP.git
cd SPSS-MCP
install.bat

Then restart Claude Code. Done!

Manual Install

# 1. Install
pip install -e .

# 2. Auto-configure Claude Code
spss-mcp configure-claude

# 3. Restart Claude Code

Configuration

Basic Setup

Recommended: let SPSS-MCP auto-configure Claude Code for you:

spss-mcp configure-claude

This command:

• detects your SPSS installation
• merges mcpServers.spss into Claude Code's user config (~/.claude.json)
• creates a timestamped backup before updating existing settings

If you prefer manual setup, add this to Claude Code settings (Ctrl+, → search mcpServers):

{
  "mcpServers": {
    "spss": {
      "command": "spss-mcp",
      "args": ["serve", "--transport", "stdio"]
    }
  }
}

SPSS Path (if not auto-detected)

Create .env file:

SPSS_INSTALL_PATH=C:\Program Files\IBM\SPSS Statistics\31

Slow SPSS startup?

If SPSS itself launches slowly on your machine, increase the engine startup timeout:

SPSS_STARTUP_TIMEOUT=300

This is separate from SPSS_TIMEOUT, which controls the timeout for each analysis job after the engine is already running.

Optional: Install Skills

Skills make analysis more reliable and auto-save results:

set SKILLS_DIR=%USERPROFILE%\.claude\skills
xcopy /E /I skills\spss-analyst "%SKILLS_DIR%\spss-analyst"
xcopy /E /I skills\spss-mcp-guard "%SKILLS_DIR%\spss-mcp-guard"

Restart Claude Code after installation.

Usage

Just describe your analysis in natural language:

请对 data.sav 进行描述性统计

分析 age 和 income 的相关性

用 t 检验比较男女收入差异

Claude will:

1. Read your data file
2. Generate SPSS syntax
3. Execute the analysis
4. Return formatted results
5. Save .spv and .sps files

Output Files

Every analysis produces:

Default location: %TEMP%\spss-mcp\results\

With skills installed: spss_result/ in your working directory

Available Tools

File & Data (9 tools)

• spss_check_status - Check server capabilities
• spss_list_files - List .sav files
• spss_list_variables - List variables with labels
• spss_read_metadata - Read variable types and labels
• spss_read_data - Preview data rows
• spss_file_summary - Get file statistics
• spss_import_csv - Convert CSV to .sav

Basic Statistics (9 tools)

• spss_frequencies - Frequency tables
• spss_descriptives - Mean, SD, min, max
• spss_crosstabs - Contingency tables with chi-square
• spss_t_test - Independent/paired/one-sample t-tests
• `spss_anov

... View full README on GitHub