Which file formats are supported?
XLSX, XLS, and CSV files are supported.
@bengbengbalabalabeng
基本信息
Model Context Protocol (MCP) for Excel.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"fastexcel-mcp-server": {
"command": "java",
"args": [
"-jar",
"<YOUR_PATH>/fastexcel-mcp-server-0.0.1-SNAPSHOT.jar"
],
"env": {
"MCP_WORKSPACES": "<YOUR_MULTIPLE_WORKSPACES_SEPARATED_BY_COMMAS>",
"CACHE_INITIAL_CAPACITY": "[OPTIONAL] <MINIMUM_TOTAL_SIZE_FOR_THE_INTERNAL_DATA_STRUCTURES> <DEFAULT: 100>",
"CACHE_MAXIMUM_SIZE": "[OPTIONAL] <MAXIMUM_NUMBER_OF_ENTRIES_THE_CACHE_MAY_CONTAIN> <DEFAULT: 1000>",
"CACHE_EXPIRE_AFTER_WRITE": "[OPTIONAL] <LENGTH_OF_TIME_AFTER_AN_ENTRY_IS_CREATED_THAT_IT_SHOULD_BE_AUTOMATICALLY_REMOVED> <DEFAULT: 35s>"
}
}
}
}`excelPath` (string): Absolute or relative path to the Excel file.
`excelPath` (string): Absolute or relative path to the Excel file.
`excelPath` (string): Absolute or relative path to the Excel file.
`excelPath` (string): Absolute or relative path to the Excel file.
Clear all cached Excel file data from memory.
Test if the specified Excel file is available in cache.
Excel MCP Server is a Java implementation of the Model Context Protocol (MCP) for reading Excel files. It provides tools to extract headers, row data, sheet names, and row counts from XLSX, XLS, and CSV files while enforcing workspace‑based path validation. The server is intended for developers who want to enable AI assistants (e.g., Claude Desktop) to interact programmatically with spreadsheet data.
Build the server with JDK 17+ GraalVM and Maven 3.9.6+ using mvn clean package -DskipTests=true. Then configure Claude Desktop by adding a server entry to claude_desktop_config.json, setting the command to java with the JAR path and the environment variable MCP_WORKSPACES (comma‑separated allowed directories). Optional cache settings can be tuned with CACHE_INITIAL_CAPACITY, CACHE_MAXIMUM_SIZE, and CACHE_EXPIRE_AFTER_WRITE. The server exposes tools such as get_total_rows_number, get_sheet_names, read_head_spec, read_rows_spec, and cache control tools.
XLSX, XLS, and CSV files are supported.
JDK 17+ (GraalVM) and Maven 3.9.6+ are required to build and run the server.
The server only allows operations on files located inside directories listed in the `MCP_WORKSPACES` environment variable (comma‑separated). Paths outside those directories are rejected.
Yes. Environment variables `CACHE_INITIAL_CAPACITY`, `CACHE_MAXIMUM_SIZE`, and `CACHE_EXPIRE_AFTER_WRITE` let you control the internal cache parameters. Defaults are 100, 1000, and 35 seconds respectively.
The server communicates over standard I/O (stdio) as a subprocess of the MCP host (e.g., Claude Desktop). No authentication or network configuration is required.
A curated list of references for MLOps
不止于 CSS
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
🚀 The fast, Pythonic way to build MCP servers and clients.
Open-source MCP to use Blender with any LLM
评论