excel-analytics-mcp 0.1.0

Self-evolving Excel analytics toolkit — MCP server + dashboard for Claude Desktop

Excel Analytics MCP Server

A self-evolving data analytics toolkit for Claude Desktop. Drop your Excel files in, ask questions in plain English, and build up a personal library of reusable analysis tools — no coding required.

What It Does

• Upload Excel/CSV files via a beautiful web dashboard
• Ask Claude questions about your data in natural language
• Save analyses as reusable tools you can run again and again
• Create custom tools that Claude can use on your behalf
• Everything stays local — your data never leaves your machine

Quick Install

bash install.sh

This will:

1. Check for Python 3.10+ and install uv if needed
2. Set up the ~/.excel-mcp/ directory
3. Install all dependencies
4. Configure Claude Desktop automatically

Then restart Claude Desktop and you're ready to go.

How to Use

1. Upload Your Data

Open the dashboard at http://localhost:8765 (available once Claude Desktop starts the server) and drag your Excel or CSV files into the upload zone.

2. Ask Claude Questions

In Claude Desktop, try prompts like:

• "What datasets do I have?"
• "Describe the sales table"
• "Show me the top 10 customers by revenue"
• "What's the average order value by month?"
• "Find all invoices over $5,000 from last week"

3. Save Reusable Analyses

When you find a useful query, ask Claude to save it:

• "Save this as a tool called 'Top Customers'"
• "Create a reusable analysis for monthly revenue trends"

4. Manage Your Tools

Visit the Tools tab in the dashboard to:

• View all your saved analyses and custom tools
• Edit tool parameters
• Test tools with different inputs
• Delete tools you no longer need

Dashboard

The web dashboard runs at http://localhost:8765 and provides:

• Data Manager — upload files, browse tables, preview data, see column stats
• Tool Workshop — view core tools, manage saved analyses, test tools with auto-generated forms

Architecture

Claude Desktop ←→ MCP Server (stdio) ←→ SQLite DB
                         ↓
                    REST API (port 8765) ←→ Web Dashboard

The MCP server communicates with Claude Desktop via stdio, while a REST API runs in a background thread to power the dashboard. Both share the same SQLite database and tool registry.

Available Tools

Core Tools (always available)

Tool	Description
list_datasets	Show all loaded tables
describe_dataset	Column info, types, stats
query	Run read-only SQL queries
summarize	Statistical summary of tables/columns

Meta Tools (for building your toolkit)

Tool	Description
save_analysis	Save a SQL query as a reusable tool
create_tool	Build a custom Python tool (sandboxed)
list_my_tools	See all your saved tools
edit_tool	Update an existing tool
delete_tool	Remove a tool
test_tool	Run a tool with test parameters

Security

• SQL: Read-only queries only (SELECT). No writes, drops, or schema changes.
• Python tools: Sandboxed execution with restricted imports. No file system access, no network, no dangerous operations.
• Local only: All data stored in ~/.excel-mcp/. Nothing leaves your machine.

File Locations

Path	Purpose
~/.excel-mcp/data.db	SQLite database with your data
~/.excel-mcp/tools/	Saved analyses and custom tools
~/.excel-mcp/output/	Tool output files
~/.excel-mcp/config.json	User configuration

Configuration

Edit ~/.excel-mcp/config.json:

{
  "data_dir": "~/Documents",
  "port": 8765,
  "auto_scan": false
}

Development

# Install dependencies
uv sync

# Run the server directly (for testing)
uv run python -m excel_mcp

License

MIT