Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-excel-reader Show me the first rows of /data/report.xlsx"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server untuk baca file Excel (.xlsx, .xls). Gratis, open source, tanpa API key.
Baca file Excel (.xlsx, .xls)
Tampilkan jumlah baris & kolom
Tampilkan nama-nama kolom
Tampilkan 5 baris pertama sebagai preview
Error handling yang clean
Related MCP server: Excel Explorer
git clone https://github.com/username/mcp-excel-reader.git
cd mcp-excel-reader
npm install
npm run buildnpm startnpx @modelcontextprotocol/inspectorBuka browser ke http://localhost:6274, lalu connect:
Command: node
Arguments: dist/server.js
Working Directory: /path/to/mcp-excel-gratis
Tambahkan di claude_desktop_config.json:
{
"mcpServers": {
"mcp-excel-gratis": {
"command": "node",
"args": ["/path/to/mcp-excel-gratis/dist/server.js"]
}
}
}read_excelInput:
Parameter | Type | Description |
| string | Path lengkap ke file Excel |
Output:
{
"filePath": "/path/to/file.xlsx",
"sheetName": "Sheet1",
"rowCount": 100,
"columnCount": 5,
"columnNames": ["Name", "Email", "Phone", "City", "Value"],
"firstFiveRows": [
{
"Name": "John Doe",
"Email": "john@example.com",
"Phone": "08123456789",
"City": "Jakarta",
"Value": 1500000
}
]
}The MCP server successfully reads Excel workbook data through the read_excel tool.
TypeScript
MIT
Inputs: filePath (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 1 tool
With only one tool, there is no potential for confusion between tools. The name 'read_excel' clearly indicates its purpose, making it unambiguous.
The single tool follows a clear verb_noun naming pattern (read_excel), and there are no other tools to introduce inconsistency.
Having only one tool is too few for an Excel reader, which typically needs operations like listing sheets, reading specific ranges, or fetching metadata. This feels thin for the server's stated purpose.
The server only offers a single 'read_excel' operation, leaving gaps for specifying sheets, ranges, or handling different data formats. This is a significant limitation for a comprehensive Excel reading experience.
Read-only MCP over your Excel or Airtable plus the PDFs beside it, joined as one relational dataset.
Let AI agents read, check and edit Excel models. Open a workbook or drop in one MCP config. Either way: typed cells, a formula dependency graph, and a verification certificate. Deterministic — no OCR, no model guessing at your numbers.
Hosted MCP: CSV/XLSX to JSON rows and text-PDF pages; private uploads or URLs, no API key.
Convert Apple Numbers (.numbers) to Excel (.xlsx) in the browser — first sheet free. MCP v1.1.0 (Streamable HTTP) exposes four tools: open_numbers2excel (open site / Stripe checkout intents; conversion is browser-local), get_site_info (product overview, pricing, URLs; read-only), get_pro_status (Stripe subscription_id sub_… status), get_unlock_from_session (Checkout session_id cs_… → entitlement). Path A: MCP does not accept or upload files.
