This is a basic test server built on the Smithery platform that demonstrates two simple capabilities: greeting users by name and scraping webpage content. It's essentially a starter template showing how to build and deploy MCP servers through Smithery's infrastructure. The greeting tool is the main example in the code, while the scraping functionality appears to use Playwright with Firefox under the hood (hence the shared memory requirement in Docker). You'd use this as a reference implementation if you're learning to build MCP servers with Smithery, or fork it as a starting point for your own tools. It's streamable HTTP only and requires a Smithery API key to run.
An MCP server built with Smithery.
Run the server:
uv run dev
Test interactively:
uv run playground
Try saying "Say hello to John" to test the example tool.
Build the image (from the project root):
docker build -t hello-server .
Run the container:
docker run --rm -p 8081:8081 --shm-size=1g hello-server
Notes:
0.0.0.0:8081 and serves the MCP endpoint at /mcp.--shm-size=1g improves browser stability for Playwright/Firefox-based scraping.You can now connect an MCP client to:
http://localhost:8081/mcp
Your server code is in src/hello_server/server.py. Add or update your server capabilities there.
Ready to deploy? Push your code to GitHub and deploy to Smithery:
Create a new repository at github.com/new
Initialize git and push to GitHub:
git add .
git commit -m "Hello world 👋"
git remote add origin https://github.com/YOUR_USERNAME/YOUR_REPO.git
git push -u origin main
Deploy your server to Smithery at smithery.ai/new
com.mcparmory/google-search
io.github.pipeworx-io/brave-search
marcopesani/mcp-server-serper
brave/brave-search-mcp-server
com.mcparmory/google-search-console
acamolese/google-search-console-mcp