Advertise
MCP.so
Sign In

MCP Analyst

@unravel-team

Repository

Basic information

Category

Data & Analytics

Transports

stdio

Author

unravel-team

About MCP Analyst

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

MCP Analyst config

Add this server to your MCP-compatible client using the configuration below.

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

MCP Analyst tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is MCP Analyst?

MCP Analyst is an MCP server that empowers Claude to analyze local CSV or Parquet files. It is intended for datasets larger than the context window or when uploading the full file is not desired to optimize cost.

How to use MCP Analyst?

Install uv (required runtime) then add the server to your Claude desktop configuration file with the command uvx mcp-analyst --file_location <path_to_csv_or_parquet_files>. On macOS the config is at ~/Library/Application Support/Claude/claude_desktop_config.json; on Windows at %APPDATA%/Claude/claude_desktop_config.json.

Key features of MCP Analyst

  • Works with local CSV and Parquet files
  • Handles datasets larger than Claude’s context window
  • Reduces cost by avoiding full file uploads
  • Supports file globs for batch analysis
  • Installed via uvx with a single command

Use cases of MCP Analyst

  • Analyze large CSV exports without uploading the entire file
  • Query local Parquet datasets that exceed context limits
  • Run cost‑efficient data analysis by loading only needed rows
  • Process multiple CSV files in a directory using glob patterns

Frequently asked questions

1

What file formats does MCP Analyst support?

MCP Analyst supports CSV and Parquet files.

2

How can I analyze more than one CSV file?

Use a glob pattern in the `--file_location` argument, for example `data/*.csv` to include all CSV files in the `data` directory.

3

What runtime is required to run MCP Analyst?

The server requires `uv` (installable via Homebrew on macOS or `winget` on Windows).

4

Where is the server configuration defined?

The server is added to Claude’s desktop configuration file (`claude_desktop_config.json`) under the `mcpServers` key.

Comments

More Data & Analytics MCP servers

SocialAPIs — Facebook & Instagram Data

SocialAPIsHub

Facebook & Instagram data for AI agents — pages, posts, groups, Ads Library, Marketplace, profiles and reels. 47 read-only tools with structured output.

1

Rankbits

rankbits

AI visibility analytics across 15+ providers (ChatGPT, Perplexity, Gemini, AI Overviews, and more). The MCP connector lets assistants run scans, compare competitor mentions, and track your brand's visibility in AI answer

AI Website Auditor

Armstrong Holdco LLC

Check whether ChatGPT, Claude, Perplexity and Gemini recommend a business, right from your AI agent. Get a 0 to 100 AI visibility score with a per-engine breakdown, the competitor named in your place, a full site audit,

Forency

cheevahagadog

Investigate any website's technology stack: CMS, eCommerce, frameworks, analytics, CRM, payments, and hosting behind any URL. Ask "which of these 15 prospects use HubSpot vs Salesforce?" and get a table back. Free tier:

1

TikTok MCP Server

HasData

Hosted TikTok MCP server for AI agents: read public profiles, account videos, comments and replies, or search videos and creators. Structured JSON for creator research and content analysis.

3
Advertise