local-llm-mcp

sandraschi/local-llm-mcp

3.2

If you are the rightful owner of local-llm-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

Local-LLM-MCP is a high-performance local LLM server integrated with FastMCP 2.12+ and vLLM 1.0+ for efficient model context protocol operations.

Tools

Functions exposed to the LLM to take actions

Health Check

Server status and performance metrics

System Info

Hardware compatibility and resource usage

Model Management

Load/unload models with automatic optimization

Load Model

Initialize with V1 engine and FlashAttention 3

Text Generation

19x faster inference with streaming support

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources