Excel MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 245 installs a week from pypi. Last commit 10 Aug 2026.
Read real, messy Excel files from an agent: multiple sheets, title rows, merged cells.
Today is the operative word: we check Excel MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add excel-mcp -- uvx excel-agent-mcp
{
"mcpServers": {
"excel-mcp": {
"args": [
"excel-agent-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.excel-mcp]
command = "uvx"
args = ["excel-agent-mcp"]
{
"mcpServers": {
"excel-mcp": {
"args": [
"excel-agent-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"excel-mcp": {
"args": [
"excel-agent-mcp"
],
"command": "uvx"
}
}
}
An MCP enabled multi-format document reader supporting DOCX, PDF, TXT, and Excel files
An Excel-compatible spreadsheet engine for agents: deterministic formulas, block memory, real .xlsx.
Excel tools for AI agents: read/write, decompile to F#/C#/XML/JSON, or build from XML/JSON.
Convert XLSX, XLS and CSV files from URLs to JSON rows; pay-per-event via your Apify account.
Read and filter Excel, ODS, CSV, SQLite, Parquet and MTSV files — or a directory — as plain text
End-to-end tests from one sentence: an agent drives a real browser, and passing runs replay free.
Turn analyzed data into an Excel-like spreadsheet at a shareable URL: formulas, styles, filters.
Normalizes messy Excel spreadsheets into canonical JSON, mapping any headers to 19 standard fields.
Answers built from our own checks of this server.