Skip to main content
Glama

20 Best Spreadsheets MCP Servers, Compared (November 2026)

Updated 20 of 951 Spreadsheets servers in the Glama registryRebuilt weekly

The short answer

For most developers, Excel MCP Server (haris-musa/excel-mcp-server) is the one to install first: it had 4,278 GitHub stars, 35,333 PyPI downloads in a typical week, 46 tools, and a commit 1 day ago. It is for editing Excel workbooks without Microsoft Excel, so it fits local file work on Windows, macOS, and Linux. If you need Google Sheets editing and formatting, mcp-gsheets (freema/mcp-gsheets) is the better answer: it exposes 44 tools and had a commit 11 days ago. It also had 2,849 npm downloads in a typical week.

Whichever you choose, give it the narrowest access that still works (a read-only credential, a replica, a scratch account), and widen it only once you have watched what your agent actually asks for.

Glama operates the MCP registry these numbers are measured from, and sells MCP hosting and a gateway. No position on this page is paid for. How the registry is built.

Quick picks

  • 1Excel MCP Server : Editing Excel workbooks without Microsoft Excel: it exposes workbook, range, chart and PivotTable tools over MCP on Windows, macOS and Linux.
  • 2Excel MCP Server (uses Excel App, 100% Compatibility) : Automating a workbook on Windows with Excel installed: it drives the real Excel application through COM, preserving macros, PivotTables, and formatting.
  • 3mcp-gsheets : Editing and formatting existing Google Sheets from an MCP client: it exposes 44 tools for reading, writing, formatting, charts, and table operations.
  • 4Microsoft 365 MCP Server : Editing Excel workbook data and formatting from an AI assistant: it exposes table, row, range, worksheet, chart, and range-format tools via Microsoft Graph.
  • 5mcp-google-sheets : Automating Google Sheets from an MCP client: it bridges to Google Drive and Sheets with documented CRUD, listing, batching, sharing, and formatting operations.

Which one, for your situation

Your situationWhat to use
I need to edit local Excel workbooks without ExcelExcel MCP Server (haris-musa/excel-mcp-server) is the direct fit: it had 46 tools, 35,333 PyPI downloads in a typical week, and a commit 1 day ago.
I need Google Sheets editing and formattingmcp-gsheets (freema/mcp-gsheets) exposes 44 tools for reading, writing, formatting, charts, and table operations and had a commit 11 days ago.
I need Excel through Microsoft 365 GraphMicrosoft 365 MCP Server (Softeria/ms-365-mcp-server) exposes table, row, range, worksheet, chart, and range-format tools through Microsoft Graph and had 44,401 npm downloads in a typical week.
Agents need multi-turn xlsx edits with recalculationspreadsheet-mcp (PSU3D0/agent-spreadsheet) is the stateful option with dry-run, recalculation, and diff/proof flows, and it had 141 commits in the last 12 weeks.
I need to convert XLSX and Office documents to MarkdownDocling-rs MCP (docling-project/docling.rs) exposes convert and convert_to_markdown tools and had 1,497 commits in the last 12 weeks.
I need to keep spreadsheet rows and columns when copying cellsmcp-clipboard (cmeans/mcp-clipboard) reads the system clipboard and preserves tabular structure as Markdown, JSON, or CSV with 7 tools.

Top MCP servers for Spreadsheets

Profile
1Community favourite4,278+5735.3Kyesterday88.1
2Community favourite847+39–2 days ago81.5
3Community favourite104+12.8K11 days ago77.4
4Community favourite1,114+10044.4Kyesterday71.2
5Abandoned but popular1,016+426.1K175 days ago66.2
6Emerging128+36–today62.8
7Community favourite2,900+64819.8Ktoday55.9
8Steady63+5–58 days ago54.7
9Abandoned but popular11027399 days ago53.8
10Community favourite1,063+313962 days ago49.2
11Steady3804275 days ago44.7
12Steady79+1–18 days ago42.7
13Steady41+5–yesterday42.3
14Steady4105638 days ago41.5
15Steady43+1–19 days ago41.1
16Steady11+1–yesterday40.8
17Steady408217 days ago40.5
18Dormant950–126 days ago40.1
19Abandoned but popular163-1–142 days ago39.7
20Steady809844 days ago39.6

The ranking, with the evidence

  • Best for: Editing Excel workbooks without Microsoft Excel: it exposes workbook, range, chart and PivotTable tools over MCP on Windows, macOS and Linux.

    Excel MCP Server exposes 46 tools for creating and editing workbooks, sheets, ranges, formulas, charts, PivotTables, tables, conditional formatting, validation and layout, and it reads VBA in .xlsm files. The README's quick start assumes uv, launches it with uvx excel-mcp-server stdio against an allowed workbook directory, and notes that it runs on openpyxl without Microsoft Excel.

    Score 88.1: show every number behind it
    • Adoption98 / 100 · weight 40%
      • GitHub stars91
      • PyPI downloads48
        PyPI downloads show no weekday rhythm; halved
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum53 / 100 · weight 14%
      • Stars gained, relative to size47
      • Stars gained, absolute71
      • PyPI download trend42
    • Tool quality66 / 100 · weight 13%
      • Tool description quality57
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    88.1
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    88.1
  • Best for: Automating a workbook on Windows with Excel installed: it drives the real Excel application through COM, preserving macros, PivotTables, and formatting.

    The README documents an MCP server and CLI for controlling Microsoft Excel through its COM API, covering Power Query, DAX, VBA, Python in Excel, PivotTables, charts, ranges, and formulas. Before choosing it, note that it requires Windows, Microsoft Excel 2016 or later, and an interactive desktop, so it is not intended for Linux, macOS, or server-side batch processing.

    Score 81.5: show every number behind it
    • Adoption73 / 100 · weight 40%
      • GitHub stars73
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum75 / 100 · weight 14%
      • Stars gained, relative to size81
      • Stars gained, absolute64
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    81.5
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    81.5
  • Best for: Editing and formatting existing Google Sheets from an MCP client: it exposes 44 tools for reading, writing, formatting, charts, and table operations.

    mcp-gsheets is a Node.js MCP server that exposes 44 tools for reading, writing, formatting, charting, and managing Google Sheets through MCP clients such as Claude Desktop. Before use it requires a Google Cloud project with the Sheets API enabled, a service account JSON key, and the target spreadsheet shared with that service account.

    Score 77.4: show every number behind it
    • Adoption81 / 100 · weight 40%
      • GitHub stars51
      • npm downloads74
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance92 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade80
      • Commit cadence85
    • Momentum36 / 100 · weight 14%
      • Stars gained, relative to size31
      • Stars gained, absolute16
      • npm download trend69
    • Tool quality68 / 100 · weight 13%
      • Tool description quality60
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    77.4
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    77.4
  • Best for: Editing Excel workbook data and formatting from an AI assistant: it exposes table, row, range, worksheet, chart, and range-format tools via Microsoft Graph.

    The server exposes 202 tools that connect AI assistants to Microsoft 365 through the Graph API, including authentication and account selection, OneDrive file operations, Excel tables and ranges, and batch Graph requests. The server requires Microsoft account authentication through MSAL, so a configured Microsoft account is needed before its Graph API tools can be used.

    Score 71.2: show every number behind it
    • Adoption100 / 100 · weight 40%
      • GitHub stars76
      • npm downloads99
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance95 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade80
      • Commit cadence100
    • Momentum90 / 100 · weight 14%
      • Stars gained, relative to size100
      • Stars gained, absolute81
      • npm download trend84
    • Tool quality53 / 100 · weight 13%
      • Tool description quality45
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    91.3
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    71.2
  • Best for: Automating Google Sheets from an MCP client: it bridges to Google Drive and Sheets with documented CRUD, listing, batching, sharing, and formatting operations.

    mcp-google-sheets is a Python MCP server that connects an MCP-compatible client to Google Drive and Google Sheets and documents tools for creating, reading, updating, listing, batching, sharing, and formatting spreadsheets. Before choosing it, set up Google Cloud Platform credentials and enable the necessary APIs, with a service account recommended and environment variables such as SERVICE_ACCOUNT_PATH and DRIVE_FOLDER_ID used in the documented quick start.

    Score 66.2: show every number behind it
    • Adoption82 / 100 · weight 40%
      • GitHub stars75
      • PyPI downloads47
        PyPI downloads show no weekday rhythm; halved
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance46 / 100 · weight 24%
      • Last commit touching this server68
      • Repository maintenance grade30
      • Commit cadence5
    • Momentum32 / 100 · weight 14%
      • Stars gained, relative to size24
      • Stars gained, absolute29
      • PyPI download trend51
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    66.2
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    66.2
  • Best for: Converting XLSX workbooks and other Office documents into Markdown for AI agents: it exposes convert and convert_to_markdown tools that handle XLSX, DOCX, PPTX, and HTML.

    The server exposes three tools, convert, convert_to_markdown, and list_input_formats, converting documents such as PDF, XLSX, DOCX, PPTX, HTML, e-mail, images, and audio into Markdown or docling JSON. For PDF, image, and audio conversion it requires the ONNX models to be downloaded first, whereas Office, HTML, Markdown, and e-mail formats need no models.

    Score 62.8: show every number behind it
    • Adoption59 / 100 · weight 40%
      • GitHub stars53
      • npm downloadsnot measured
        no npm package
      • Used through Glama39
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum85 / 100 · weight 14%
      • Stars gained, relative to size100
      • Stars gained, absolute63
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality93 / 100 · weight 13%
      • Tool description quality85
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integrates100
    Weighted mean of the five
    80.5
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    62.8
  • 7

    kordoc

    Community favourite
    chrisryugj/kordoc ↗

    Best for: Extracting tables from South Korean administrative files (HWP, HWPX, PDF, XLS/XLSX, scans) into Markdown: it reconstructs merged cells and enables OCR for scans.

    kordoc is a library, CLI, and MCP server that converts HWP, HWPX, HWPML, PDF, XLS/XLSX, DOCX, PPTX, and image files into Markdown or structured data. Before choosing it, note that it requires Node.js 20 or later.

    Score 55.9: show every number behind it
    • Adoption93 / 100 · weight 40%
      • GitHub stars87
      • npm downloads46
        downloads show none of the weekday rhythm human traffic has; halved
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum100 / 100 · weight 14%
      • Stars gained, relative to size100
      • Stars gained, absolute100
      • npm download trend100
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    93.2
    × relevance: the keyword is tagged here
    0.60
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    55.9
  • Best for: Agents doing multi-turn edits on .xlsx workbooks that must be recalculated and verified: it is a stateful MCP server with dry-run, recalculation and diff/proof flows.

    It ships a stateful MCP server alongside an asp CLI and a TypeScript SDK, covering reads, writes, recalculation and verification through deterministic JSON contracts, with preview-first write helpers and grouped verify proof / verify diff checks. Two limits matter before installing: .xls and .xlsb workbooks are read-only for discovery-style workflows, and default in-process calculation depends on the project's own Formualizer engine rather than Excel or headless LibreOffice.

    Score 54.7: show every number behind it
    • Adoption45 / 100 · weight 40%
      • GitHub stars45
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance88 / 100 · weight 24%
      • Last commit touching this server88
      • Repository maintenance grade80
      • Commit cadence100
    • Momentum52 / 100 · weight 14%
      • Stars gained, relative to size66
      • Stars gained, absolute32
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    64.4
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    54.7
  • Best for: Game configuration management in Excel: it documents SQL queries and update, insert, and delete operations for cross-sheet and batch workbook changes.

    The README documents an MCP interface for SQL queries, updates, inserts, and deletes across Excel sheets, along with sheet structure management, formatting, and backups. It requires Python 3.10 or later and is distributed as the PyPI package excel-mcp-server-fastmcp.

    Score 53.8: show every number behind it
    • Adoption56 / 100 · weight 40%
      • GitHub stars27
      • PyPI downloads52
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance57 / 100 · weight 24%
      • Last commit touching this server88
      • Repository maintenance grade30
      • Commit cadence5
    • Momentum0 / 100 · weight 14%
      • Stars gained, relative to size0
      • Stars gained, absolute0
      • PyPI download trendnot measured
        no download history for the selected registry
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    53.8
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    53.8
  • Best for: Reading PDFs in a project context: the read_pdf tool extracts content and metadata from local or URL files and accepts page selections for each source.

    The server exposes one tool, read_pdf, which reads content and metadata from one or more local or URL PDFs and lets each source specify pages to extract. It requires Node 18+ and relies on installed local doc-VLM models or tesseract for OCR, with OCR setup requiring explicit opt-in.

    Score 49.2: show every number behind it
    • Adoption84 / 100 · weight 40%
      • GitHub stars76
      • npm downloads55
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum51 / 100 · weight 14%
      • Stars gained, relative to size66
      • Stars gained, absolute61
      • npm download trend13
    • Tool quality63 / 100 · weight 13%
      • Tool description quality55
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    82.0
    × relevance: the keyword is tagged here
    0.60
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    49.2
  • Best for: When an MCP client needs local Excel or CSV reading, writing, and analysis: it exposes cell, range, write, formatting, and financial-analysis tools.

    It runs over stdio as a local npm package and exposes 35 tools for reading, writing, formatting, analyzing, cleaning, and bulk-processing Excel and CSV files. Before choosing it, note that the AI-powered tools send spreadsheet content to a configured provider unless all provider keys are left unset, in which case a local fallback is used.

    Score 44.7: show every number behind it
    • Adoption45 / 100 · weight 40%
      • GitHub stars40
      • npm downloads35
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance76 / 100 · weight 24%
      • Last commit touching this server88
      • Repository maintenance grade80
      • Commit cadence40
    • Momentum0 / 100 · weight 14%
      • Stars gained, relative to size0
      • Stars gained, absolute0
      • npm download trend0
    • Tool quality56 / 100 · weight 13%
      • Tool description quality48
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    52.6
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    44.7
  • Best for: Creating Excel reports and charts from local spreadsheets in a Docker-isolated, offline document workflow: the README documents read-only source data and exports output.

    The server documents a local workspace interface for ordinary ChatGPT conversations: it reads, searches, edits, and moves files, produces Word, Excel, PowerPoint, PDF, and chart outputs, runs Python and terminal commands, and manages processes or named SSH hosts. It is an alpha source install that requires Python and uv, with Docker needed for document work and an OpenAI private tunnel and runtime key for ordinary ChatGPT connectivity.

    Score 42.7: show every number behind it
    • Adoption48 / 100 · weight 40%
      • GitHub stars48
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum26 / 100 · weight 14%
      • Stars gained, relative to size32
      • Stars gained, absolute16
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    64.4
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    42.7
  • Best for: Checking whether an iWork automation MCP server is available on the current platform: it provides the iwork_status tool for that check.

    iwork-mcp exposes the iwork_status tool and documents local stdio and OAuth-protected Streamable HTTP interfaces for automating Numbers, Pages, and Keynote through JavaScript for Automation. Before choosing it, note the platform requirement: macOS 13 or newer with current iWork applications and Node.js 18 or newer, plus Automation permission on first use.

    Score 42.3: show every number behind it
    • Adoption41 / 100 · weight 40%
      • GitHub stars41
      • npm downloadsnot measured
        npm names no repository for iwork-mcp, so its downloads cannot be attributed
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance97 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence85
    • Momentum53 / 100 · weight 14%
      • Stars gained, relative to size67
      • Stars gained, absolute31
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality61 / 100 · weight 13%
      • Tool description quality53
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    63.8
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    42.3
  • Best for: Agents that must build or modify a real Excel workbook: it exposes named-block creation, formula evaluation, and save_workbook to write a genuine .xlsx file.

    logisheets-mcp is an MCP server over the LogiSheets Rust spreadsheet engine, with 31 tools for creating and editing named blocks, evaluating Excel-style formulas, building charts and pivots, and saving genuine .xlsx files. It runs locally, opens no sockets, and loads or saves workbooks through filesystem paths, so the agent needs access to the .xlsx files it should work on.

    Score 41.5: show every number behind it
    • Adoption43 / 100 · weight 40%
      • GitHub stars41
      • npm downloads19
        downloads show none of the weekday rhythm human traffic has; halved
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum8 / 100 · weight 14%
      • Stars gained, relative to size0
      • Stars gained, absolute0
      • npm download trend32
    • Tool quality85 / 100 · weight 13%
      • Tool description quality77
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    62.6
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    41.5
  • Best for: AI workflows that need Word, Excel, PowerPoint, email, or XML files generated on request: the README documents a dedicated creation tool for each format.

    The README documents MCP tools for creating PowerPoint presentations, Word documents from Markdown, Excel workbooks from Markdown, email drafts, and XML files. The quick-start path uses Docker Compose and an MCP endpoint at http://localhost:8958/mcp, with files saved locally by default unless cloud or LibreChat storage is configured.

    Score 41.1: show every number behind it
    • Adoption41 / 100 · weight 40%
      • GitHub stars41
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum27 / 100 · weight 14%
      • Stars gained, relative to size35
      • Stars gained, absolute16
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    62.0
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    41.1
  • Best for: Editing VBA in Excel, Word, PowerPoint or Access files: it reads and writes modules with guarded edits and runs macros on Windows with Office.

    It exposes 65 tools for reading, writing, analyzing and testing VBA in Excel, Word, PowerPoint and Access files, along with form, Power Query, worksheet and document edits. Running macros and tests requires Windows with the desktop Office application, while the VBA, Power Query and OOXML worksheet layer needs no Office installation.

    Score 40.8: show every number behind it
    • Adoption27 / 100 · weight 40%
      • GitHub stars27
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum29 / 100 · weight 14%
      • Stars gained, relative to size38
      • Stars gained, absolute15
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality81 / 100 · weight 13%
      • Tool description quality73
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    58.3
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: small audience
    0.70
    Composite score
    40.8
  • Best for: Copying spreadsheet cells into AI chat without losing rows and columns: it reads the system clipboard and preserves tabular structure as Markdown, JSON, or CSV.

    mcp-clipboard exposes seven clipboard tools, with clipboard_paste for reading and clipboard_copy, clipboard_copy_image, and clipboard_copy_markdown for writing, plus raw-format and version diagnostics. It requires an MCP-compatible client and reads from or writes to the system clipboard, so spreadsheet data must be on the clipboard before it can be read.

    Score 40.5: show every number behind it
    • Adoption43 / 100 · weight 40%
      • GitHub stars17
      • PyPI downloads41
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance93 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence65
    • Momentum0 / 100 · weight 14%
      • Stars gained, relative to size0
      • Stars gained, absolute0
      • PyPI download trendnot measured
        no download history for the selected registry
    • Tool quality96 / 100 · weight 13%
      • Tool description quality88
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    61.1
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    40.5
  • Best for: File-based Excel, CSV, and JSON analysis and editing through an MCP client: eight tools cover reading, writing, updating, filtering, pivoting, summarizing, analyzing, and charting.

    Excel MCP Server exposes eight tools named read_excel, write_excel, update_excel, analyze_excel, filter_excel, pivot_table, export_chart, and data_summary, plus README-documented resource URIs and prompt templates. It is distributed as the PyPI package mcp-excel-server and depends on pandas, numpy, matplotlib, and seaborn.

    Score 40.1: show every number behind it
    • Adoption50 / 100 · weight 40%
      • GitHub stars50
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance40 / 100 · weight 24%
      • Last commit touching this server68
      • Repository maintenance grade5
      • Commit cadence5
    • Momentum0 / 100 · weight 14%
      • Stars gained, relative to size0
      • Stars gained, absolute0
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality68 / 100 · weight 13%
      • Tool description quality60
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    47.2
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    40.1
  • Best for: Generating and filling Office documents locally: it ships as a Rust binary documented for Excel, Word, PowerPoint, PDF export and PDF form filling.

    Its README documents a cargo-installable binary launched over stdio, with configuration snippets for Claude Desktop, Cursor and VS Code, and showcases XLSX, DOCX, PPTX and PDF-export output alongside PDF form filling. No npm or PyPI package is published, so installation assumes a Rust toolchain or a download from GitHub Releases, and the exposed tool list has not been inspected.

    Score 39.7: show every number behind it
    • Adoption55 / 100 · weight 40%
      • GitHub stars55
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance46 / 100 · weight 24%
      • Last commit touching this server68
        dated from the last commit on the default branch, re-read from GitHub at publication; github.com shows a push 36 days ago, which counts every ref; the stored date would have published 36 days ago
      • Repository maintenance grade30
      • Commit cadence5
    • Momentum0 / 100 · weight 14%
      • Stars gained, relative to size0
      • Stars gained, absolute0
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integrates100
    Weighted mean of the five
    50.9
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    39.7
  • Best for: Windows users automating local Excel, PowerPoint, or Word files through an MCP client: it provides separate local servers with allowlisted roots and write toggles.

    MCP Office is a suite of local MCP servers for Windows that expose Microsoft Excel, PowerPoint, and Word file automation to an MCP client over stdio, with allowlist roots and write-enable environment variables. It requires Windows 10 or 11 and, for COM-backed tools such as styling, PDF export, and tracked changes, a local Microsoft Office installation.

    Score 39.6: show every number behind it
    • Adoption46 / 100 · weight 40%
      • GitHub stars24
      • PyPI downloads42
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance88 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade80
      • Commit cadence65
    • Momentum18 / 100 · weight 14%
      • Stars gained, relative to size0
      • Stars gained, absolute0
      • PyPI download trend71
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    59.7
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    39.6

Questions people ask

Is mcp-google-sheets (xing5/mcp-google-sheets) still active?

It is labeled Abandoned but popular. It had a commit 175 days ago and 0 commits in the last 12 weeks, while still showing 26,103 PyPI downloads in a typical week and 1,016 GitHub stars. If you need recent commits, choose another Google Sheets server.

How do I choose between Excel MCP Server (haris-musa/excel-mcp-server) and spreadsheet-mcp (PSU3D0/agent-spreadsheet)?

Choose Excel MCP Server (haris-musa/excel-mcp-server) for broad workbook editing without Microsoft Excel, with 46 tools and 35,333 PyPI downloads in a typical week. Choose spreadsheet-mcp (PSU3D0/agent-spreadsheet) when an agent needs multi-turn edits with dry-run, recalculation, and diff/proof flows; it had 141 commits in the last 12 weeks and a commit 58 days ago.

Does Excel MCP Server (haris-musa/excel-mcp-server) require Microsoft Excel?

It edits Excel workbooks without Microsoft Excel and runs on Windows, macOS, and Linux. It had 46 tools and 35,333 PyPI downloads in a typical week.

What should I watch out for with Microsoft 365 MCP Server (Softeria/ms-365-mcp-server)?

It exposes 202 tools, and its tool descriptions were graded C, so review them before letting an agent edit workbook data and formatting. It had 44,401 npm downloads in a typical week and a commit 1 day ago, so the broad tool surface is the thing to manage.

What does Docling-rs MCP (docling-project/docling.rs) do with an XLSX file?

It converts XLSX workbooks and other Office documents into Markdown or docling JSON. It exposes 3 tools, including convert and convert_to_markdown, and had 1,497 commits in the last 12 weeks. It is not the workbook editing route described for Excel MCP Server (haris-musa/excel-mcp-server).

How do I keep spreadsheet rows and columns when copying cells into an AI chat?

Use mcp-clipboard (cmeans/mcp-clipboard): it reads the system clipboard and preserves tabular structure as Markdown, JSON, or CSV. It exposes 7 tools and had a commit 17 days ago.

Other comparisons