Browse
→ AI & Models
→ AMD Lemonade MCP Server
AMD Lemonade MCP Server
Open source local LLM server from AMD that runs language models on Ryzen AI PCs with NPU acceleration and now includes MCP server integration as of version 10.8 released June 17, 2026. Provides a local, private inference endpoint compatible with MCP tool calling, enabling AI agents to use locally-running models for reasoning and tool execution without cloud dependencies. Supports streaming tool calls and works with Hugging Face Tiny Agents and other MCP-compatible frameworks. Designed for developers who want fully local, private AI agent capabilities on AMD hardware. MIT licensed on GitHub under lemonade-sdk.
MCP unverified
Integration
| Transport | stdio |
| Auth | none |
| Endpoint | amd-lemonade-mcp |
Use Cases
| 01 | Run AI agents entirely on-device using AMD Ryzen AI NPU acceleration with MCP tool calling for private, cloud-free inference |
| 02 | Connect Hugging Face Tiny Agents and other MCP-compatible frameworks to a local Lemonade server for tool-augmented reasoning on AMD hardware |
| 03 | Build edge AI agent workflows that execute MCP tools locally without sending data to external services, using AMD NPU for fast on-device inference |
Tags
local-llm amd ryzen-ai npu private edge-ai open-source
Machine-readable: /api/servers.json
· JSON-LD schema embedded in <head>