--- title: Connect to Hosted Server description: Use mcwaddams without installing anything locally. --- import { Aside, Code, Tabs, TabItem, Card, CardGrid } from '@astrojs/starlight/components'; > *"I was told there would be no installation..."* Don't want to install anything? Connect to our hosted mcwaddams server via HTTP. ## Quick Connect ```bash claude mcp add mcwaddams-hosted --transport http "https://mcwaddams.l.supported.systems/mcp" ``` ```json { "mcpServers": { "mcwaddams": { "transport": { "type": "streamable-http", "url": "https://mcwaddams.l.supported.systems/mcp" } } } } ``` ```python from mcp import ClientSession from mcp.client.streamable_http import streamable_http_client async with streamable_http_client("https://mcwaddams.l.supported.systems/mcp") as (read, write): async with ClientSession(read, write) as session: await session.initialize() tools = await session.list_tools() print(f"Connected! {len(tools.tools)} tools available") ``` ## What's Available All 20+ mcwaddams tools are available via the hosted server: Extract text, images, metadata from Word, Excel, PowerPoint Process `.doc`, `.xls`, `.ppt` files from the 90s Index documents and fetch chapters/sheets on demand Multiple extraction methods with automatic fallback ## Hosted vs Local | Feature | Hosted | Local (uvx) | |---------|--------|-------------| | Installation | None | `uvx mcwaddams` | | File Access | URL only | Local + URL | | Speed | Network latency | Instant | | Privacy | Files processed on server | Files stay local | | Availability | Requires internet | Works offline | ## Using with URLs The hosted server can process documents from URLs directly: ```python # Extract text from a public document result = await session.call_tool("extract_text", { "file_path": "https://example.com/report.docx" }) ``` This is particularly useful for processing documents already hosted online. ## Self-Hosting Want the convenience of HTTP without using our server? Self-host your own: ### Docker Compose ```yaml services: mcwaddams: image: ghcr.io/ryanmalloy/mcwaddams:latest environment: - MCP_TRANSPORT=streamable-http - MCP_HOST=0.0.0.0 - MCP_PORT=8000 ports: - "8000:8000" ``` ### With Caddy Reverse Proxy Clone the repo and use our docker-compose with caddy-docker-proxy labels: ```bash git clone https://github.com/ryanmalloy/mcwaddams.git cd mcwaddams cp .env.example .env # Edit .env to set your hostname make docker-up ``` Your server will be available at `https://your-domain.com/mcp` ### Local Development Run HTTP mode locally without Docker: ```bash # Install pip install mcwaddams # Run with HTTP transport MCP_TRANSPORT=streamable-http MCP_HOST=127.0.0.1 MCP_PORT=8000 python -m mcwaddams.server ``` Or with uv: ```bash MCP_TRANSPORT=streamable-http MCP_HOST=127.0.0.1 MCP_PORT=8000 uvx mcwaddams ``` ## Troubleshooting ### Connection Refused ``` Error: Connection refused ``` The server may be temporarily down. Try: 1. Check server status at https://status.supported.systems 2. Fall back to local installation: `uvx mcwaddams` ### Timeout Errors Large documents may take longer to process. The hosted server has a 60-second timeout per request. For very large documents, consider: - Using local installation - Processing documents in chunks via pagination ### SSL/TLS Errors Ensure you're using `https://` not `http://`. The hosted server requires TLS. ---
*"So if you could just go ahead and connect... that would be great."*