MCP server for comparing Excel files with hierarchical module matching (stacked output)
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"excel-diff2-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# excel-diff2-mcp MCP (Model Context Protocol) server for comparing Excel files with hierarchical module matching. ## Features - **Hierarchical Module Matching**: Match Excel data by multiple levels of functional modules - **Stacked Output**: Output two tables stacked in a single result - **Dual Output Formats**: Support both CSV and Markdown output - **Flexible Input**: Accept HTTP(S) URLs or Base64-encoded file content - **Auto Header Detection**: Automatically detect header rows - **Merged Cell Handling**: Fill merged cells downward for accurate comparison ## Installation ```bash pip install excel-diff2-mcp ``` ## Usage ### Command Line ```bash excel-diff2-mcp ``` ### As MCP Tool ```python from mcp.client.session import Session async with Session() as session: result = await session.call( "compare_excel", file1="https://example.com/file1.xlsx", file2="https://example.com/file2.xlsx", compare_columns=["一级功能模块", "二级功能模块"], output_format="markdown", # optional: "csv" (default) or "markdown" ) ``` ### compare_excel Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `file1` | str | Yes | First Excel file (URL or Base64 content) | | `file2` | str | Yes | Second Excel file (URL or Base64 content) | | `compare_columns` | list | Yes | Columns for hierarchical matching | | `table_name1` | str | No | Display name for table 1 | | `table_name2` | str | No | Display name for table 2 | | `output_format` | str | No | Output format: `"csv"` (default) or `"markdown"` | ### compare_columns Formats **Single array** (same columns for both tables): ```python ["一级功能模块", "二级功能模块"] ``` **Dual array** (different columns per table): ```python [["一级功能模块", "二级功能模块"], ["一级功能点", "二级功能点"]] ``` ## Output ### CSV Format ```csv 表1名称,,,, 一级功能模块,二级功能模块,描述,比对结果 模块A,子模块1,描述内容,一级、二级功能模块均在【表2】找到 模块B,子模块2,描述内容,一级功能模块在【表2】找到 表2名称,,,, 一级功能模块,二级功能模块,描述,比对结果 模块A,子模块1,描述内容,一级、二级功能模块均在【表1…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.