MCP Hub
Back to servers

mcp-ragchat

An MCP server that enables RAG-powered AI chat integration for websites by crawling content, building local vector stores, and generating embeddable chat widgets. It simplifies the setup of local chat servers with support for various LLM and embedding providers.

Updated
Feb 20, 2026

mcp-ragchat

An MCP server that adds RAG-powered AI chat to any website. One command from Claude Code.

License: MIT Node.js 20+ TypeScript MCP npm


Tell Claude Code "add AI chat to mysite.com" and it will crawl your content, build a local vector store, spin up a chat server, and hand you an embed snippet. No cloud infra. No database. Just one API key.

Demo

You:    "Set up AI chat for mybakery.com using this FAQ and menu content"

Claude: I'll set up RAG-powered chat for mybakery.com.

        [1/4] ragchat_setup
              Splitting content into sections...
              Generating embeddings for 12 documents...
              Domain "mybakery.com" configured with 12 documents.

        [2/4] ragchat_test
              Query: "What are your hours?"
              Reply: "We're open Monday-Saturday 7am-6pm, and Sunday 8am-2pm."
              RAG Sources: mybakery.com-3 (0.91), mybakery.com-7 (0.84)
              Latency: 340ms

        [3/4] ragchat_serve
              Chat server running at http://localhost:3456
              POST /chat ready.

        [4/4] ragchat_widget
              Generated embed code. Paste this into your HTML:

              <script src="http://localhost:3456/widget.js"></script>

You:    Done. Live chat on my site in under 60 seconds.

Quick Start

1. Clone and build

git clone https://github.com/gogabrielordonez/mcp-ragchat
cd mcp-ragchat
npm install && npm run build

2. Configure Claude Code (~/.claude/mcp.json)

{
  "mcpServers": {
    "ragchat": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-ragchat/dist/mcp-server.js"],
      "env": {
        "OPENAI_API_KEY": "sk-..."
      }
    }
  }
}

3. Use it

Open Claude Code and say:

"Add AI chat to mysite.com. Here's the content: [paste your markdown]"

Claude handles the rest.

Tools

ToolWhat it does
ragchat_setupSeed a knowledge base from markdown content. Each ## section becomes a searchable document with vector embeddings.
ragchat_testSend a test message to verify RAG retrieval and LLM response quality.
ragchat_serveStart a local HTTP chat server with CORS and input sanitization.
ragchat_widgetGenerate a self-contained <script> tag -- a floating chat bubble, no dependencies.
ragchat_statusList all configured domains with document counts and config details.

How It Works

                        +------------------+
                        |  Your Markdown   |
                        +--------+---------+
                                 |
                          ragchat_setup
                                 |
                    +------------v-------------+
                    |   Local Vector Store      |
                    |   ~/.mcp-ragchat/domains/ |
                    |     vectors.json          |
                    |     config.json           |
                    +------------+-------------+
                                 |
          User Question          |
               |                 |
        +------v------+  +------v------+
        |  Embedding  |  |  Cosine     |
        |  Provider   +->+  Similarity |
        +-------------+  +------+------+
                                |
                         Top 3 chunks
                                |
                    +----------v-----------+
                    |  System Prompt       |
                    |  + RAG Context       |
                    |  + User Message      |
                    +----------+-----------+
                               |
                    +----------v-----------+
                    |     LLM Provider     |
                    +----------+-----------+
                               |
                            Reply

Everything runs locally. No cloud infrastructure. Bring your own API key.

Supported Providers

LLM (chat completions)

ProviderEnv VarDefault Model
OpenAIOPENAI_API_KEYgpt-4o-mini
AnthropicANTHROPIC_API_KEYclaude-sonnet-4-5-20250929
Google GeminiGEMINI_API_KEYgemini-2.0-flash

Embeddings (vector search)

ProviderEnv VarDefault Model
OpenAIOPENAI_API_KEYtext-embedding-3-small
Google GeminiGEMINI_API_KEYtext-embedding-004
AWS BedrockAWS_REGION + IAMamazon.titan-embed-text-v2:0

Override defaults with LLM_MODEL and EMBEDDING_MODEL environment variables.

Architecture

~/.mcp-ragchat/domains/
  mysite.com/
    config.json     -- system prompt, settings
    vectors.json    -- documents + embedding vectors
  • Vector store -- Local JSON files with cosine similarity search. Zero external dependencies.
  • Chat server -- Node.js HTTP server with CORS and input sanitization.
  • Widget -- Self-contained <script> tag. No frameworks, no build step.

Contributing

Issues and pull requests are welcome.

Star History

Star History Chart


Enterprise

Need multi-tenancy, security guardrails, audit trails, and managed infrastructure? Check out Supersonic -- the enterprise AI platform built on the same RAG pipeline.


MIT License -- Gabriel Ordonez

Reviews

No reviews yet

Sign in to write a review