excel-mcp
Let your AI agent read real, messy Excel files. An MCP server that handles the things LLMs choke on: multiple sheets, title rows sitting above the actual table, and merged cells.
If you paste a spreadsheet into a prompt, the model has to guess where the data starts and what the merged cells mean, and it often gets it wrong. This reads the file properly with deterministic code, so the values are exact and the model never invents cell contents.
The problem it solves
A real spreadsheet almost never starts cleanly at cell A1:
A1: Quarterly Sales Report 2024 <- title, not data
A2: Generated by finance <- note, not data
A3: (blank)
A4: Region | Product | Units <- the actual header
A5: North | Widget | 120
...
Ask an LLM to read that and it'll often treat the title as a column. read_table auto-detects that
the header is on row 4 and returns clean records. Merged cells (a value spanning several rows) get
forward-filled, so rows don't lose their category.
The tools it gives an agent
| Tool | What it does |
|---|---|
list_sheets(path) | Every sheet in the workbook, with its size |
preview_sheet(path, sheet, rows) | Top rows as a grid, so the agent can see the layout |
read_table(path, sheet) | The actual data table as records (auto-detects the header row) |
sheet_to_csv(path, sheet) | The table as clean CSV text |
Quickstart
pip install "excel-agent-mcp[mcp]"
Add it to your MCP client (e.g. Claude Desktop):
{
"mcpServers": {
"excel": { "command": "excel-agent-mcp" }
}
}
Now your agent can answer "what's in this spreadsheet?" or "pull the sales table out of sheet 2" by reading the file, not guessing.
Also usable from plain Python
from excel_mcp import reader
reader.list_sheets("report.xlsx")
reader.read_table("report.xlsx", "Sales") # {'columns': [...], 'rows': [...], 'header_row': 3}
reader.sheet_to_csv("report.xlsx", "Sales")
Tests
python -m unittest discover -s tests # builds its own messy xlsx, runs anywhere
License
MIT