Schema | VLLM MCP Server

Server Configuration

Describes the environment variables required to run the server.

Name	Required	Description	Default
`PYTHONPATH`	No	Python path for module resolution	src
`VLLM_MCP_HOST`	No	Server host (optional)	localhost
`VLLM_MCP_PORT`	No	Server port (optional)	8080
`OPENAI_API_KEY`	No	Your OpenAI API key
`OPENAI_BASE_URL`	No	OpenAI base URL (optional)	https://api.openai.com/v1
`DASHSCOPE_API_KEY`	Yes	Your Dashscope API key
`VLLM_MCP_LOG_LEVEL`	No	Log level (optional)	INFO
`VLLM_MCP_TRANSPORT`	No	Transport type (optional)	stdio
`OPENAI_DEFAULT_MODEL`	No	Default OpenAI model to use	gpt-4o
`DASHSCOPE_DEFAULT_MODEL`	No	Default Dashscope model to use	qwen-vl-plus
`OPENAI_SUPPORTED_MODELS`	No	Comma-separated list of supported OpenAI models	gpt-4o,gpt-4o-mini,gpt-4-turbo,gpt-4-vision-preview
`DASHSCOPE_SUPPORTED_MODELS`	No	Comma-separated list of supported Dashscope models	qwen-vl-plus,qwen-vl-max,qwen-vl-chat,qwen2-vl-7b-instruct,qwen2-vl-72b-instruct

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

Name Description

Name	Description
generate_multimodal_response	Generate response from multimodal model. `Args: model: Model name to use prompt: Text prompt image_urls: Optional list of image URLs file_paths: Optional list of file paths system_prompt: Optional system prompt max_tokens: Maximum tokens to generate temperature: Generation temperature provider: Optional provider name (openai, dashscope) Returns: Generated response text`
list_available_providers	List available model providers and their configurations. `Returns: JSON string of available providers and their models`
validate_multimodal_request	Validate if a multimodal request is supported. `Args: model: Model name to validate image_count: Number of images in request file_count: Number of files in request provider: Optional provider name Returns: Validation result`

generate_multimodal_response

Generate response from multimodal model.

        Args:
            model: Model name to use
            prompt: Text prompt
            image_urls: Optional list of image URLs
            file_paths: Optional list of file paths
            system_prompt: Optional system prompt
            max_tokens: Maximum tokens to generate
            temperature: Generation temperature
            provider: Optional provider name (openai, dashscope)

        Returns:
            Generated response text

list_available_providers

List available model providers and their configurations.

        Returns:
            JSON string of available providers and their models

validate_multimodal_request

Validate if a multimodal request is supported.

        Args:
            model: Model name to validate
            image_count: Number of images in request
            file_count: Number of files in request
            provider: Optional provider name

        Returns:
            Validation result

Prompts

Interactive templates invoked by user choice

Name	Description
No prompts

Resources

Contextual data attached and managed by the client

Name	Description
No resources

VLLM MCP Server

Server Configuration

Capabilities

Tools

Prompts

Resources

Latest Blog Posts

MCP directory API