# Turnstone MCP Server

A [Model Context Protocol](https://modelcontextprotocol.io/) server providing four sandboxed, production-ready tools for LLM-driven workflows. Built with **FastMCP** and **Playwright**, it exposes code execution, headless browser automation, and file-to-Markdown conversion over HTTP.

## Tools

| Tool | Description |
|---|---|
| `execute_python_code` | Runs Python source in a subprocess with timeout, memory, and output-size limits |
| `playwright_navigate` | Navigates a persistent headless Chromium session to a URL |
| `playwright_get_page_text` | Extracts rendered text from the current browser page |
| `extract_to_markdown` | Converts supported files (PDF, DOCX, images, CSV, etc.) to Markdown via `markitdown` |

## Quick Start

```bash
# Install dependencies
pip install fastmcp playwright markitdown
playwright install chromium

# Run the server
python server.py
```

The server starts on `http://0.0.0.0:8000`. The MCP health endpoint is available at `/health`.

## Configuration

All limits are configurable via environment variables with sensible defaults:

| Variable | Default | Description |
|---|---|---|
| `PYTHON_EXEC_TIMEOUT` | `30` | Python execution timeout (seconds) |
| `PYTHON_MAX_OUTPUT` | `65536` | Maximum stdout/stderr capture (bytes) |
| `PYTHON_MAX_MEMORY_MB` | `256` | Address-space memory limit per subprocess (MB) |
| `PLAYWRIGHT_NAV_TIMEOUT` | `30000` | Browser navigation timeout (ms) |
| `PLAYWRIGHT_TEXT_TIMEOUT` | `15000` | Page text extraction timeout (ms) |
| `EXTRACT_MAX_FILE_SIZE` | `10485760` | Maximum file size for extraction (10 MB) |
| `WORKSPACE_ROOT` | `/workspace` | Base directory for file-relative operations |

Example with custom limits:

```bash
PYTHON_EXEC_TIMEOUT=60 PYTHON_MAX_MEMORY_MB=512 python server.py
```

## Architecture

```
┌──────────────┐     HTTP/MCP      ┌──────────────────┐
│   LLM Client │ ────────────────► │  Turnstone MCP    │
│              │                   │  Server :8000     │
└──────────────┘                   └────────┬─────────┘
                                            │
                    ┌───────────────────────┼───────────────────────┐
                    │                       │                       │
              ┌─────▼─────┐          ┌──────▼──────┐       ┌───────▼───────┐
              │ subprocess │          │ Playwright  │       │ markitdown    │
              │ (Python)   │          │ Chromium    │       │ (file → MD)   │
              └───────────┘          └─────────────┘       └───────────────┘
```

### Key design decisions

- **Persistent browser session** — A singleton `PlaywrightBrowserManager` holds the Chromium process alive across tool calls, preventing garbage-collection teardowns.
- **Sandboxed execution** — Python code runs in a separate process with a per-subprocess memory limit (`resource.setrlimit`) and a wall-clock timeout enforced by `subprocess.run`.
- **Path traversal protection** — `extract_to_markdown` resolves all paths against `WORKSPACE_ROOT` and rejects anything that escapes it.
- **Structured JSON logging** — All tool invocations and responses are logged as structured JSON for observability.
- **CORS enabled** — The server accepts requests from any origin with standard MCP headers.

## Endpoints

| Method | Path | Description |
|---|---|---|
| `POST` | `/` | MCP protocol endpoint (default) |
| `GET` | `/health` | Returns `{"status": "healthy", "service": "turnstone-mcp"}` |

## Project Structure

```
server.py          # Complete MCP server — all logic in a single module
```

This repository is intentionally minimal: one file, zero dependencies beyond the pip requirements.

## Development

No test framework or build step is required. To add a new tool, follow the existing pattern:

1. Define the function with `@mcp.tool()`
2. Add docstring with `Parameters` and `Returns` sections
3. Implement input validation and error handling
4. Return a string result (success or error message)

## License

See the repository root for licensing information.