sitebox
Enables AI agents to upload, list, read, and delete static web pages via the Model Context Protocol, with REST API and optional authentication and TTL.
README
sitebox
Self-hosted static site host — upload pages via REST API or MCP, serve them immediately.
- Upload files or ZIP archives to named destinations
- Serve from
/dest/pathinstantly - Auth — shared API key for uploads, optional password-protected pages
- TTL — auto-expire pages after a set time
- MCP — AI agents can manage pages via the built-in Model Context Protocol server
Quick start
docker run -e API_KEY=my-secret-key -v /path/to/pages:/app/data -p 8000:8000 ghcr.io/zarguell/sitebox
Upload a page:
curl -X POST http://localhost:8000/api/upload \
-H "X-API-Key: my-secret-key" \
-F "file=@index.html" \
-F "dest=myapp"
Open http://localhost:8000/myapp/index.html in your browser.
Features
REST API
| Method | Path | Description |
|---|---|---|
POST |
/api/upload |
Upload file or ZIP to a destination |
GET |
/api/pages |
List all pages |
DELETE |
/api/pages/{dest} |
Delete a page |
All require X-API-Key header matching the API_KEY environment variable.
Upload parameters (multipart form):
| Field | Required | Description |
|---|---|---|
file |
yes | The file (ZIP auto-extracts and flattens) |
dest |
yes | Destination path (e.g. myapp or blog/post1) |
auth_required |
no | true to require login before viewing |
ttl_seconds |
no | Auto-delete after N seconds |
MCP Server
Connect an MCP-compatible AI agent (Cursor, Claude Desktop) to http://host:8000/mcp with header X-API-Key.
Available tools:
upload_page— upload base64 content or ZIPlist_pages— browse page treeread_file— read file contentdelete_page— remove a page
Browser Auth
When auth_required=true on upload, visitors are redirected to a login form. The password is the shared API_KEY. Sessions last 24 hours (in-memory).
Configuration
| Env var | Required | Default | Description |
|---|---|---|---|
API_KEY |
yes | "" |
Shared secret for all auth (upload + login) |
Development
git clone https://github.com/zarguell/sitebox
cd sitebox
uv sync
API_KEY=dev-key uv run uvicorn sitebox.app:app --reload
Design
- config.py — shared env vars and in-memory state (
AUTH_PREFIXES,DATA_DIR) - storage.py — file operations (stdlib only)
- auth.py — login form, session tokens, browser auth helper
- rest_api.py — REST endpoints with API key check
- mcp_api.py — MCP server with Streamable HTTP transport
- app.py — FastAPI wiring, middleware, mounts
ponytail: session tokens and auth prefixes are in-memory (lost on restart). Add Redis or SQLite when multi-process persistence is needed.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.