rukuma-dev
MCP server for rukuma.dev enabling semantic search, page reading, page listing, and site metadata retrieval.
README
rukuma.dev — Agentic Website
An agentic website built entirely on Cloudflare's free tier ($0/month).
What's Live
| URL | What | Status |
|---|---|---|
| https://rukuma.dev | Home page (static site) | ✅ |
| https://rukuma.dev/blog | Blog listing page | ✅ |
| https://rukuma.dev/search | AI-powered semantic search UI | ✅ |
| https://rukuma.dev/mcp | Stateless MCP server (4 tools) | ✅ |
| https://rukuma.dev/llms.txt | LLM documentation index | ✅ |
| https://rukuma.dev/robots.txt | Agent-friendly robots.txt | ✅ |
| https://rukuma.dev/sitemap.xml | XML sitemap | ✅ |
| https://rukuma.dev/manifest.json | Web manifest | ✅ |
| https://rukuma.dev/api/health | Health check | ✅ |
| https://rukuma.dev/api/pages | List all pages (JSON) | ✅ |
| https://rukuma.dev/api/page/:slug | Get page detail (JSON) | ✅ |
| https://rukuma.dev/api/search | Semantic search (POST) | ✅ |
| https://rukuma.dev/api/agent-stats | AI agent visit analytics | ✅ |
| https://rukuma.dev/md/:slug | Markdown for agents | ✅ |
| https://rukuma.dev/json/:slug | JSON for agents | ✅ |
Stack
- Worker: Single Cloudflare Worker (the 1 allowed on free plan)
- D1: Content storage (pages, analytics, agent visits) — 5GB free
- KV: Edge caching (page cache, API response cache)
- Vectorize: Semantic search index (1024-dim bge-m3 embeddings)
- Workers AI: Embedding generation (bge-m3) — 10K Neurons/day free
- Static Assets: HTML/CSS/JS served from the Worker
MCP Tools
The /mcp endpoint exposes 4 tools for AI agents:
- search(query, limit?) — Semantic search across all content
- read_page(slug) — Get full markdown of any page
- list_pages(category?) — List all available pages
- site_info() — Site metadata and capabilities
Cron Jobs
| Schedule | Purpose |
|---|---|
0 */6 * * * |
Re-index content → Vectorize embeddings |
0 0 * * * |
Cleanup old analytics (>30 days) |
Deploy
export CLOUDFLARE_API_TOKEN="your-token"
# Apply D1 migrations
npx wrangler d1 migrations apply rukuma-dev-db --remote
# Seed content
python3 seed.py
# Index content into Vectorize
python3 index_content.py
# Deploy Worker
npx wrangler deploy
Project Structure
rukuma-dev/
├── wrangler.jsonc # Worker configuration
├── tsconfig.json # TypeScript config
├── src/
│ └── worker.ts # Main Worker (API + MCP + static serving)
├── public/ # Static Assets
│ ├── index.html # Home page
│ ├── blog/
│ │ └── index.html # Blog listing
│ ├── search/
│ │ └── index.html # Search UI
│ ├── css/
│ │ └── style.css # Site styling
│ └── js/
│ ├── app.js # Home page JS
│ ├── blog.js # Blog page JS
│ └── search.js # Search page JS
├── migrations/
│ └── 0001_init.sql # D1 schema
├── seed.py # D1 content seeder
├── index_content.py # Vectorize indexer
└── README.md
Cost: $0/month
Everything runs within Cloudflare's free tier limits.
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.