Grounded Docs

Open-source alternative to Context7, Nia, and Ref.Tools that solves AI hallucinations and outdated knowledge by providing a personal, always-current documentation index. Fetches official docs from websites, GitHub, npm, PyPI, and local files, allowing your AI to query the exact version you are using.

Features

• 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

Supported Formats

Processes 90+ file formats including:

• Documents: PDF, Word, Excel, PowerPoint, OpenDocument, RTF, EPUB, Jupyter Notebooks
• Web: HTML, Markdown, MDX, reStructuredText, AsciiDoc
• 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
• Archives: ZIP, TAR (contents extracted and processed)

Usage

CLI Mode

Index documentation:

npx @arabold/docs-mcp-server@latest scrape react https://react.dev/reference/react

Query the index:

npx @arabold/docs-mcp-server@latest search react "useEffect cleanup" --output yaml

Fetch a single page:

npx @arabold/docs-mcp-server@latest fetch-url https://react.dev/reference/react/useEffect

MCP Server Mode

Start the server:

npx @arabold/docs-mcp-server@latest

Open the Web UI at http://localhost:6280 to add documentation, then connect your AI client.

Docker

docker run --rm \
  -v docs-mcp-data:/data \
  -v docs-mcp-config:/config \
  -p 6280:6280 \
  ghcr.io/arabold/docs-mcp-server:latest \
  --protocol http --host 0.0.0.0 --port 6280

Embedding Models

Using an embedding model is optional but dramatically improves search quality by enabling semantic vector search. Supports OpenAI, Ollama, Gemini, Azure, and other providers.

Tools

• scrape_docs: Index documentation from websites, GitHub, or local files
• search_docs: Query indexed documentation with semantic or keyword search
• fetch_url: Fetch and convert a single URL to Markdown
• list_docs: List all indexed documentation sources
• delete_docs: Remove a documentation source from the index
• refresh_docs: Update an existing documentation source