Installation
Deploy vLLM with your GPU setup; mount the OpenAI-compatible endpoint via MCP.
MCP Server
vLLM MCP
High-throughput open-source LLM serving with PagedAttention, exposed via MCP.
AI & ML ToolsSelf-hostedAISource: vllm-project
- Author
- vllm-project
- Repository
- https://github.com/vllm-project/vllm
Use Cases
- • Self-hosted LLM inference
- • Batch generation
- • Streaming completions
Tags
llm-servingopen-sourcegpuinference
Need Implementation Help?
We can integrate vLLM MCP into your production stack, wire auth and policies, and ship a maintainable MCP setup.
View implementation service