microsoft/markitdown
MarkItDown is a Python tool that converts various file formats into Markdown and integrates with LLM applications via an MCP server for enhanced text analysis and document processing.
Awesome MCP › Other MCP Servers
yzfly/mcp-excel-server
Excel MCP Server is a Python Model Context Protocol server that gives a language model the ability to work with spreadsheet files on disk. Its reading tools open several formats, including XLSX, XLS, CSV, TSV and JSON, report file details through get_excel_info and list worksheet names through get_sheet_names. Its analysis tools cover summary and descriptive statistics with analyze_excel, condition-based filtering with filter_excel, pivot table construction with pivot_table, and a broader data_summary tool that also reports on data quality. For visualisation, export_chart renders line charts, bar charts, scatter plots and histograms from the data and writes them out as images. Two write tools complete the surface: write_excel creates new files and update_excel modifies existing ones. Alongside tools, the server exposes MCP resources addressed by URI, where excel://{file_path} returns file content, the /info suffix returns structure information about the workbook, and the /preview suffix generates a preview image of the data. It also ships MCP prompt templates that guide common workflows, namely analyze_excel_data for a walked-through analysis, create_chart for building a visualisation, and data_cleaning for tidying a dataset. The stated safety measures are reading files only from specified paths, limiting file size, guarding against accidental overwriting of existing files, and keeping data transformation operations tightly controlled. Implementation rests on the usual Python data stack of pandas, numpy, matplotlib and seaborn. Installation is a Python virtual environment created with uv or venv followed by an editable install, and the server is registered in the Claude Desktop configuration as a uvx command running mcp-excel-server with a PYTHONPATH environment entry. Typical requests are phrased in natural language, such as analysing a sales workbook, charting a CSV, filtering rows by a condition or producing a pivot table of departmental figures. MIT licensed.
https://github.com/yzfly/mcp-excel-server
Also in Other MCP Servers
punkpeye/awesome-mcp-servers
A curated collection of Model Context Protocol (MCP) servers that enable AI models to securely interact with local and remote resources through standardized server implementations.
modelcontextprotocol/servers
The Model Context Protocol Servers repository offers reference implementations and third-party integrations that demonstrate how MCP enables Large Language Models to securely access and interact with diverse tools and data sources.
koala73/worldmonitor
World Monitor is an AI-powered, real-time global intelligence dashboard aggregating news and monitoring geopolitical and infrastructure data for unified situational awareness.
headroomlabs-ai/headroom
Headroom is a context compression layer for AI agents, reducing token usage by 60-95% while preserving accuracy, implemented as a library, proxy, and MCP server.
diegosouzapw/OmniRoute
OmniRoute is a free AI gateway that connects various AI tools and models from over 230 providers through a single endpoint, featuring token compression, smart auto-fallback, and support for Model C...
rohitg00/ai-engineering-from-scratch
This comprehensive curriculum teaches AI engineering from scratch, focusing on building AI algorithms, agents, and MCP servers hands-on, covering everything from mathematical foundations to autonom...
every-app/open-seo
Open source, self-hostable SEO platform that exposes its keyword, rank, backlink and site-audit data to AI agents through an MCP server and a set of companion agent skills.