SheetForge MCP is an Excel MCP server for `.xlsx` automation over the Model Context Protocol. It is built for AI agents, MCP clients, and automation
SheetForge MCP is an Excel MCP server for .xlsx automation over the Model Context Protocol. It is built for AI agents, MCP clients, and automation workflows that
3.10+ - .xlsx workbooks - either uvx or a local package installCompare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| agent | friendly reads via suggest_read_strategy, describe_dataset, query_table, and aggregate_table |
| local | first performance and privacy with openpyxl, no desktop Excel dependency, and no cloud-auth requirement |
| suggest_read_strategy | recommends the best next read tool for a workbook target, including whether SheetForge should treat it as a native Excel table, a clean worksheet dataset, a layout-heavy dashboard sheet, or a chart sheet |
| describe_dataset | samples a worksheet or native Excel table and returns headers, schema hints, key-candidate guesses, structural signals, and a recommended follow-up read path |
| query_table | filters, projects, sorts, and limits worksheet-shaped data or native Excel tables with a declarative JSON query instead of ad hoc cell loops |
| aggregate_table | computes grouped metrics such as count, sum, avg, min, and max over worksheet-shaped data or native Excel tables |
| bulk_aggregate_workbooks | computes the same grouped metrics across many workbook files in one call, with explicit schema handling via strict, intersect, or union |
| bulk_filter_workbooks | returns matching rows across many workbook files with optional source provenance columns, so recurring cross-file QA and reporting checks no longer need one-tool-call-per-file loops |
| union_tables | combines comparable worksheet or native-table rows across many workbook files, with optional deduplication keys and explicit schema handling for workbook collections that drift over time |
| cross_workbook_lookup | enriches one workbook dataset from one or more lookup workbooks with left-join style matching, optional duplicate-match handling, and compact per-row provenance for matched lookup rows |
| profile_workbook | one-call inventory for sheets, tables, charts, named ranges, and key layout/protection state, including chart occupied_range for grid-anchored worksheet charts |
| describe_sheet_layout | worksheet-level structural summary for safe dashboard edits, including freeze panes, print settings, merges, chart anchors, table metadata, conditional-format and validation counts, custom row/column sizing, and a small |
| audit_workbook | workbook-level audit for high-signal problems such as broken #REF! formulas, error cells, hidden sheets, header-quality issues, layout-heavy sheets, and named ranges that reference missing sheets |
| plan_workbook_repairs | converts workbook audit findings into prioritized next steps, including suggested SheetForge tool calls for inspection, safe dry runs, and repair workflows |
{
"mcpServers": {
"excel": {
"command": "uvx",
"args": [
"sheetforge-mcp",
"stdio"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
3.10+ - .xlsx workbooks - either uvx or a local package installGenerates both vector and raster images using EverArt's AI models, providing flexible storage and format conversion.
Provides file system operations, analysis, and manipulation through a standardized tool interface.
A custom MCP (Model Context Protocol) server that reads and summarizes the contents of any file type (PDF, DOCX, TXT, HTML, JSON, etc.) using Apache Tika, with optional multilingual support.
Turkish gold-market digest, derived indicators and analysis search. Keyless, read-only, gated.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
스킬 구매 전 성능표와 시험 방식을 확인하세요. 표본 수·평가일·기계 검사와 모델 점수를 구분하며, 미검증 항목은 수치를 표시하지 않습니다. 공개 JSON도 제공하며 별도의 유료 도구 호출이 필요하지 않습니다.