Skip to main content
Glama

VLLM MCP Server

by StanleyChanH

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PYTHONPATHNoPython path for module resolutionsrc
VLLM_MCP_HOSTNoServer host (optional)localhost
VLLM_MCP_PORTNoServer port (optional)8080
OPENAI_API_KEYNoYour OpenAI API key
OPENAI_BASE_URLNoOpenAI base URL (optional)https://api.openai.com/v1
DASHSCOPE_API_KEYYesYour Dashscope API key
VLLM_MCP_LOG_LEVELNoLog level (optional)INFO
VLLM_MCP_TRANSPORTNoTransport type (optional)stdio
OPENAI_DEFAULT_MODELNoDefault OpenAI model to usegpt-4o
DASHSCOPE_DEFAULT_MODELNoDefault Dashscope model to useqwen-vl-plus
OPENAI_SUPPORTED_MODELSNoComma-separated list of supported OpenAI modelsgpt-4o,gpt-4o-mini,gpt-4-turbo,gpt-4-vision-preview
DASHSCOPE_SUPPORTED_MODELSNoComma-separated list of supported Dashscope modelsqwen-vl-plus,qwen-vl-max,qwen-vl-chat,qwen2-vl-7b-instruct,qwen2-vl-72b-instruct

Schema

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/StanleyChanH/vllm-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server