mcp-analyst MCP Server

Use This MCP server To

Analyze large CSV datasets locally without uploading full files Process Parquet files for data insights within Claude Handle datasets exceeding LLM context window size efficiently Use file globs to analyze multiple data files simultaneously Optimize cost by avoiding full dataset uploads to cloud Integrate local data analysis into AI workflows with Claude

README

MCP Analyst

MCP Analyst is an MCP server that empowers claude to analyze local CSV or Parquet files.

Use this server when your dataset size is bigger than the context window or you don't want to upload full file to optimize the cost.

Installation

Install uv

uv is required to run the MCP server.

Mac

brew install uv

Windows

winget install --id=astral-sh.uv  -e

Add servers in MCP

To use the server in Claude you would need to update the Claude config

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "analyst": {
      "command": "uvx",
      "args": [
        "mcp-analyst",
        "--file_location",
        "<replace_this_with_path_to_csv_or_parquet_files_on_your_machine>"
      ]
    }
  }
}

How do I provide more than one CSV file?

The server supports the using globs in the file location. So for example if your directory data has more than one csv file then you can give file-location as <parent_path_to_data>/data/*.csv

mcp-analyst FAQ

How do I install MCP Analyst?

Install the 'uv' tool via Homebrew on Mac or winget on Windows, then configure MCP Analyst as a server in your Claude config file.

Can MCP Analyst handle multiple files at once?

Yes, it supports file globs allowing you to specify multiple CSV or Parquet files for analysis.

Why use MCP Analyst instead of uploading files directly?

It processes large datasets locally, avoiding context window limits and reducing cloud upload costs.

What file formats does MCP Analyst support?

It supports CSV and Parquet file formats for data analysis.

How do I configure MCP Analyst with Claude?

Update the Claude desktop config JSON to include MCP Analyst with the file location argument pointing to your data files.

Is MCP Analyst compatible with other LLMs besides Claude?

While designed for Claude, MCP Analyst can potentially integrate with other LLMs supporting MCP, such as OpenAI's GPT-4 and Anthropic's Claude.

What is the role of the 'uv' tool in MCP Analyst?

'uv' is required to run the MCP server, acting as the runtime environment for MCP Analyst.

Can MCP Analyst analyze datasets larger than the LLM context window?

Yes, it is specifically designed to handle datasets exceeding typical LLM context limits by processing data locally.