What are the requirements for using Ragdocs?

You'll need Node.js (16+), Docker (for local Qdrant setup, recommended), and either Ollama (free, local) or an OpenAI API key (paid). See the installation instructions for details.

What integrations does Ragdocs offer?

Ragdocs integrates seamlessly with Cline, Roo-Code, and Claude Desktop via the Model Context Protocol (MCP), bringing semantic search directly to your coding and AI environments.

What credentials does it need?

It reads `QDRANT_URL`, `EMBEDDING_PROVIDER`, `OLLAMA_URL`, `OPENAI_API_KEY`, `QDRANT_API_KEY` from the environment. Store these in your client's env block or a secrets manager — never commit them to a repository — and grant the narrowest scope that still covers your use case.

SSyncDev

Start a project

Ragdocs MCP Server

Enables semantic search and retrieval of documentation using a vector database, allowing users to add and query documentation from URLs or local

Local serverstdio★ 135

What is the Ragdocs MCP Server?

Enables semantic search and retrieval of documentation using a vector database, allowing users to add and query documentation from URLs or local files using natural

The short version

A Model Context Protocol (MCP) server that enables semantic search and retrieval of documentation using a vector database (Qdrant). This server allows you to add documentation from URLs or local files and then search through them using natural language queries.

Add documentation from URLs or local files
Store documentation in a vector database for semantic search
Search through documentation using natural language
List all documentation sources

What it needs from you

Node.js 16 or higher - Qdrant (either local or cloud) - One of the following for embeddings: - Ollama running locally (default, free) - OpenAI API key (optional, paid)

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

How to install the Ragdocs MCP Server

claude mcp add ragdocs-2 --env QDRANT_URL=your-value --env EMBEDDING_PROVIDER=your-value --env OLLAMA_URL=your-value --env OPENAI_API_KEY=your-value --env QDRANT_API_KEY=your-value -- npx -y @qpd-v/mcp-server-ragdocs

Configuration

Node.js 16 or higher - Qdrant (either local or cloud) - One of the following for embeddings: - Ollama running locally (default, free) - OpenAI API key (optional, paid)

Variable	Description	Required
QDRANT_URL	Endpoint or connection string the server talks to.	Yes
EMBEDDING_PROVIDER	Configuration value read at startup.	Optional
OLLAMA_URL	Endpoint or connection string the server talks to.	Yes
OPENAI_API_KEY	Credential the server authenticates with.	Yes
QDRANT_API_KEY	Credential the server authenticates with.	Yes

Example prompts to try

“Use Ragdocs to Parameters.”

Frequently asked questions

Ragdocs is a tool that allows you to semantically search your documentation using natural language. It stores your documentation in a vector database (Qdrant) and lets you query it as if you were talking to a human expert.