Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
python-sdk
The official Python SDK for Model Context Protocol servers and clients
23.3kstars
3.5kforks
Python
Quality signals
ActiveNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Python library to build and run Model Context Protocol servers and clients for exposing data/tools to LLMs.
Use this when
- Need to expose local files as LLM-readable resources
- Want to add custom tools for LLM to call
- Building a server to integrate with Claude Code or other MCP clients
- Creating reusable prompts for LLM interactions
- Testing MCP servers with the MCP Inspector
Don't use when
- Building a non-LLM application without MCP client/server needs
- Need a simple REST API instead of MCP protocol
- Working with non-Python environments
Capabilities
- Define resources (read-only data endpoints)
- Expose tools (callable functions with arguments)
- Create reusable prompts (template-based LLM interactions)
- Support stdio, SSE, and Streamable HTTP transports
- Handle structured output for tool results
- Provide client utilities for connecting to MCP servers
InstallMCPRun via uvx (Python)
Universal installANY TOOL
$ npx skillcity@latest modelcontextprotocol/python-sdkAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor or Cline.
Requires Node.js 18+ (ships with npx).
Or install manually
uvx python-sdk
MCP Configuration
Add this to your claude_desktop_config.json
{
"mcpServers": {
"python-sdk": {
"command": "uvx",
"args": [
"python-sdk"
]
}
}
}Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
python-sdk — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt