Mcp Using Llm Demo
A Python demonstration of building an AI agent with LangChain, Qwen3 running locally through Ollama, and the GitHub Model Context Protocol (MCP) Server. The application dynamically discovers GitHub MCP tools, allows the Qwen3 LLM to select the appropriate tool, and searches GitHub repositories using the search_repositories MCP tool.
5-Factor AST Security Breakdown
Deterministic code heuristics and edge isolation analysis
Passed static AST scan: Verified absence of arbitrary remote eval, prompt injections, and unauthenticated exfiltration webhooks.
Native compatibility with Cloudflare Workers runtime, Workerd engine, or Model Context Protocol schema.
Basic open-source declaration. Explicit LICENSE file recommended.
README contains comprehensive setup guides, deployment commands, and environmental configurations.
Verified repository structure with authentic commit history (4/12 community traction, 8/8 commit provenance).
Deep Static Code & Manifest Inspection
Automated AST scan of repository configuration and security vectors
eval() or unconstrained reflectionIntegration & MCP Setup
Copy pre-formatted config snippets for your AI IDE or CLI
{
"mcpServers": {
"mcp-using-llm-demo": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-mcp-using-llm-demo"
]
}
}
}More MCP Servers Tools
View allModel Context Protocol Servers
The official Python SDK for Model Context Protocol servers and clients
The official TypeScript SDK for Model Context Protocol servers and clients