데이터분석 LangGraph Agent (w. MCP)

@gongwon-nayeon

代码仓库

基本信息

分类

推理

传输方式

stdio

作者

gongwon-nayeon

关于 데이터분석 LangGraph Agent

DataAnalysis Agent using LangGraph & MCP server and client

#langgraph #data-analysis #mcp

데이터분석 LangGraph Agent 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "langgraph-mcp-dataanalysis": {
      "command": "python",
      "args": [
        "data_server.py"
      ]
    }
  }
}

데이터분석 LangGraph Agent 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is 데이터분석 LangGraph Agent (w. Model Context Protocol)?

This project implements a Python-based MCP (Model Context Protocol) server and client for data analysis tasks (statistics, visualization, modeling) and integrates them with a LangGraph Agent using the langchain-mcp-adapters library. It is designed for users who want to build a data analysis agent that can understand natural language requests and perform operations on CSV datasets.

How to use 데이터분석 LangGraph Agent (w. Model Context Protocol)?

Install the required dependency langchain-mcp-adapters, then run python data_server.py and python data_client.py. Users can then send natural language requests such as “Give me the statistics of the petal length column in iris_data.csv” or “Visualize the distribution of the sepal length column in iris_data.csv”.

Key features of 데이터분석 LangGraph Agent (w. Model Context Protocol)

Python‑based MCP server and client setup
Data statistics, visualization, and modeling capabilities
Integration with LangGraph Agent via langchain-mcp-adapters
Natural language user input for data requests
Works with CSV datasets (e.g., iris_data.csv)

Use cases of 데이터분석 LangGraph Agent (w. Model Context Protocol)

Compute and return statistical summaries for a specific column of a CSV file
Generate a visualization of a column’s distribution
Train a predictive model using selected features and output the results
Perform ad‑hoc data analysis through conversational agent interaction

常见问题

What analysis tasks does this agent support?

The agent supports computing statistics, generating visualizations, and training machine learning models on CSV data.

What are the required dependencies?

You need Python, the `langchain-mcp-adapters` package, the MCP Python SDK, and any dependencies listed in the project (implicitly `pandas`, `matplotlib`, `scikit-learn`, etc. for data tasks).

Where does the input data come from?

The user provides a CSV file – the README example uses `iris_data.csv`.

Is this project intended for production use?

The README states that this project is part of a Fastcampus course on building AI agents; it is an educational implementation.

How do I run the server and client?

Run `python data_server.py` and in another terminal run `python data_client.py`. User input is then accepted via the client.

推理分类下的更多 MCP 服务器

Part 1. Real-Time LangGraph Agent with MCP Tool Execution

junfanz1

This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent

Task Planner MCP Server

CaptainCrouton89

An MCP (Model Context Protocol) server that helps AI assistants (like Claude) break down complex tasks into manageable steps, track progress, and manage a hierarchical task list.

Agentic Swmm Workflow

Zhonghao1995

Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM through the aiswmm runtime, reusable Skills, and MCP interfaces, with QA verification, provenance tracking, calibration support, and Codex,

MCP Sandbox

JohanLi233

Python sandboxes for llms

Unified MCP Suite

Godzilla675

A suite of Model Context Protocol (MCP) servers designed to enhance AI agent capabilities. Provides tools for media search/understanding (images, video), web information retrieval, PDF generation, and PowerPoint presentation creation, enabling agents to interact with diverse data