PixelRAG MCP Server

PixelRAG MCP Server

A visual Retrieval-Augmented Generation MCP server that renders web pages, PDFs, and design screenshots into visual tiles and enables natural language querying over them via multimodal vision embeddings.

Category
Visit Server

README

PixelRAG MCP Server 🚀

An open-source Visual Retrieval-Augmented Generation (Visual RAG) MCP server based on PixelRAG and FastMCP, designed for 24/7 remote hosting via SSE (Server-Sent Events) on platforms like Railway.

🌟 Features

  • Visual RAG Tooling: Render web pages, PDFs, or design screenshot folders into visual tiles and query them via multimodal vision embeddings.
  • FastMCP SSE Transport: Exposed over HTTP/HTTPS with Server-Sent Events for 24/7 remote access by Antigravity, Claude Code, Cursor, and VS Code.
  • Production Ready Docker Setup: Includes Playwright headless Chromium pre-configured for web page screenshot rendering.

🛠️ Included Tools

  1. index_document: Renders visual tiles from PDF files, image folders, or live URLs, building an indexed vector space.
  2. query_visual_index: Queries screenshot tiles using natural language prompts.
  3. health_check: Returns operational status of the MCP server.

🚀 Deploying to Railway

  1. Click + New Project $\rightarrow$ Deploy from GitHub repo.
  2. Select pixelrag-mcp-server.
  3. In Settings $\rightarrow$ Networking, click Generate Domain.
  4. Use your public SSE URL:
    https://<YOUR-RAILWAY-APP>.up.railway.app/sse

🔌 Connecting to Antigravity / MCP Client

Add the following to your MCP settings file:

{
  "mcpServers": {
    "pixelrag": {
      "url": "https://<YOUR-RAILWAY-APP>.up.railway.app/sse"
    }
  }
}

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured