Grounded Docs MCP Server is an open-source documentation indexing tool that provides AI coding assistants with accurate, version-specific documentation from official sources. It fetches and indexes documentation from websites, GitHub repositories, npm, PyPI, and local files to ground LLM responses in real, up-to-date information rather than outdated training data. Key features: - Fetches documentation on-demand from websites, GitHub repos, local folders, and zip archives - Supports 90+ file formats including PDF, Word, Excel, PowerPoint, EPUB, Jupyter Notebooks, Markdown, and source code files - Queries target exact library versions in your project for version-specific context - Runs entirely locally with no code leaving your network - Works with any MCP-compatible client including Claude, Cline, and other AI assistants - Provides CLI and web interfaces with structured output in JSON or YAML formats - Reduces AI hallucinations by grounding responses in actual documentation

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Docs MCP Server solves the problem of AI hallucinations and outdated knowledge by providing a personal, always-current documentation index for your AI coding assistant.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.

✨ Why Grounded Docs MCP Server?

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

---

📄 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

For agents and scripts, the CLI is usually the simplest way to use Grounded Docs.

1. Index documentation (requires Node.js 22+):

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

2. Query the index:

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

3. Fetch a single page as Markdown:

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

Output Behavior

Agent Skills

The skills/ directory contains Agent Skills that teach AI coding assistants how to use the CLI — covering documentation search, index management, and URL fetching.

MCP Server

If you want a long-running MCP endpoint for Claude, Cline, Copilot, Gemini CLI, or other MCP clients:

1. Start the server:

npx @arabold/docs-mcp-server@latest

2. Open the Web UI at http://localhost:6280 to add documentation.

3. Connect your AI client by adding this to your MCP settings (e.g., claude_desktop_config.json):

{
  "mcpServers": {
    "docs-mcp-server": {
      "type": "sse",
      "url": "http://localhost:6280/sse"
    }
  }
}

See Connecting Clients for VS Code (Cline, Roo) and other setup options.

Alternative: Run with 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

🧠 Configure Embedding Model (Recommended)

Using an embedding model is optional but dramatically improves search quality by enabling semantic vector search.

Example: Enable OpenAI Embeddings

OPENAI_API_KEY="sk-proj-..." npx @arabold/docs-mcp-server@latest

See Embedding Models for configuring Ollama, Gemini, Azure, and others.

---

📚 Documentation

Getting Started