Anirbanbasu Py MCP server
{
"mcpServers": {
"smithery-anirbanbasu-py": {
"type": "http",
"url": "https://server.smithery.ai/@anirbanbasu/pymcp/mcp"
}
}
}{
"mcpServers": {
"smithery-anirbanbasu-py": {
"type": "http",
"url": "https://server.smithery.ai/@anirbanbasu/pymcp/mcp"
}
}
}{
"mcpServers": {
"smithery-anirbanbasu-py": {
"type": "http",
"url": "https://server.smithery.ai/@anirbanbasu/pymcp/mcp"
}
}
}{
"servers": {
"smithery-anirbanbasu-py": {
"type": "http",
"url": "https://server.smithery.ai/@anirbanbasu/pymcp/mcp"
}
}
}{
"mcpServers": {
"smithery-anirbanbasu-py": {
"type": "http",
"url": "https://server.smithery.ai/@anirbanbasu/pymcp/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 0.1.7
What it does
A template MCP server built with FastMCP in Python that demonstrates server implementation patterns. It provides tools for greeting, password generation, web search, mathematical calculations, and Python code execution, along with a resource for retrieving the server's logo.
- Use as a starting point template when building new MCP servers in Python with FastMCP.
- Execute arbitrary Python code within a sandboxed environment for computations or data processing.
- Perform web searches and retrieve results programmatically with configurable region and result limits.
Tools this server exposes
| Tool | Does |
|---|---|
| greet | Greets the caller with a timestamped hello message, optionally including a provided name. |
| generate_password | Generates a random password of specified length (8-64 characters) with configurable special character inclusion and complexity requirements. |
| text_web_search | Searches the web using DuckDuckGo Distributed Global Search with configurable region, result count, and page spreading. |
| permutations | Calculates the number of permutations for choosing k items from n items without repetition and with order. |
| run_python_code | Executes arbitrary Python code in a sandboxed interpreter using Pydantic Monty with optional type checking and type definitions. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.