Happy slice of mcp pizzaMCP.pizza

docs-mcp-server

MCP.Pizza Chef: arabold

Point it at a website, a code repository, a folder on your computer, or a zip file, and it builds a private index your assistant can look things up in. Because answers come from documents you indexed yourself, they match the version in front of you instead of whatever the model happens to remember. It runs entirely on your machine. A key for OpenAI, Gemini, or a local model is optional but makes searching noticeably better.

Coding
Files/PDF
Web/Research

Use This MCP server To

Look up how a tool works in the version I actually installed Index a documentation site so I can ask it questions Search my own PDFs, Word files, and notes in one place Stop getting answers based on outdated documentation Keep everything I index on my own computer

README

Grounded Docs: Your AI's Up-to-Date Documentation Expert

Docs MCP Server solves the problem of AI hallucinations and outdated knowledge by providing a personal, always-current documentation index for your AI coding assistant. It fetches official docs from websites, GitHub, npm, PyPI, and local files, allowing your AI to query the exact version you are using.

Docs MCP Server Web Interface

✨ Why Grounded Docs MCP Server?

The open-source alternative to Context7, Nia, and Ref.Tools.

  • ✅ Up-to-Date Context: Fetches documentation directly from official sources on demand.
  • 🎯 Version-Specific: Queries target the exact library versions in your project.
  • 💡 Reduces Hallucinations: Grounds LLMs in real documentation.
  • 🔒 Private & Local: Runs entirely on your machine; your code never leaves your network.
  • 🧩 Broad Compatibility: Works with any MCP-compatible client (Claude, Cline, etc.).
  • 📁 Multiple Sources: Index websites, GitHub repositories, local folders, and zip archives.
  • 📄 Rich File Support: Processes HTML, Markdown, PDF, Office documents (Word, Excel, PowerPoint), OpenDocument, RTF, EPUB, Jupyter Notebooks, and 90+ source code languages.

📄 Supported Formats

Category Formats
Documents PDF, Word (.docx/.doc), Excel (.xlsx/.xls), PowerPoint (.pptx/.ppt), OpenDocument (.odt/.ods/.odp), RTF, EPUB, FictionBook, Jupyter Notebooks
Archives ZIP, TAR, gzipped TAR (contents are extracted and processed individually)
Web HTML, XHTML
Markup Markdown, MDX, reStructuredText, AsciiDoc, Org Mode, Textile, R Markdown
Source Code TypeScript, JavaScript, Python, Go, Rust, C/C++, Java, Kotlin, Ruby, PHP, Swift, C#, and many more
Data JSON, YAML, TOML, CSV, XML, SQL, GraphQL, Protocol Buffers
Config Dockerfile, Makefile, Terraform/HCL, INI, dotenv, Bazel

See Supported Formats for the complete reference including MIME types and processing details.

🚀 Quick Start

CLI First

docs-mcp-server FAQ

Which assistants can use it?
Claude, VS Code with Cline or Roo, Copilot, Gemini CLI, and any other assistant that supports MCP.
What can it index?
Websites, GitHub repositories, npm and PyPI packages, local folders, and zip archives, covering PDFs, Word, Excel, PowerPoint, Markdown, and dozens of code formats.
Do I need a paid key?
No, it works without one. Adding an OpenAI, Gemini, Ollama, or Azure key turns on smarter searching by meaning.
How hard is setup?
You run one command to start it, open a page in your browser to add documentation, then paste a short block into your assistant's settings. A container version is also available.
Can I use this to answer questions about my company's internal docs?
Yes — point it at a local folder or a zip file and it indexes those exactly as it would a public site.
Does my code leave my machine?
No. It runs locally and your files stay on your own network.