This repository provides local Python MCP examples for arithmetic, DuckDuckGo search and page retrieval, alongside a Groq-powered host.
This repository provides local Python MCP examples for arithmetic, DuckDuckGo search and page retrieval, alongside a Groq-powered host.
The repository combines an assistant host with separate MCP server scripts. math_server.py implements addition and multiplication. duckduckgo_server.py implements search and page-content retrieval. The Groq integration belongs to the assistant host; these local arithmetic and web tools do not themselves require a Groq credential. The package metadata points to an upstream search package, so source-file launch commands are clearer than assuming a new package published by this repository.
The project requires Python 3.10 or later and uses SDK 1 FastMCP imports. Keep compatible SDK 1 dependencies or migrate the imports when installing the environment. Register each script as its own stdio server after installing its dependencies. Web search and retrieval require network access, while the arithmetic example operates locally.
Start with an addition whose answer you know, then search for a public page and compare the retrieved content with the page itself. A search result is a pointer to a source, not a verified answer. Keep these examples distinct from planned email or other microservices discussed in the architecture: those capabilities are not established by the two inspected server scripts.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| add | Add two numbers. |
| multiply | Multiply two numbers. |
| search | Search through DuckDuckGo. |
| fetch_content | Retrieve content from a web page. |
{
"mcpServers": {
"math-example": {
"command": "python",
"args": [
"/ABSOLUTE_PATH/MCP-GROQ/math_server.py"
]
}
}
}Python 3.10 or later, the project dependencies, compatible MCP SDK 1 imports and network access for the web-search example.
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.