vllm-mcp

StanleyChanH/vllm-mcp

3.3

If you are the rightful owner of vllm-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.

A Model Context Protocol (MCP) server that enables text models to call multimodal models, supporting both OpenAI and Dashscope multimodal models.

Tools

Functions exposed to the LLM to take actions

generate_multimodal_response

Generate responses from multimodal models.

list_available_providers

List available model providers and their supported models.

validate_multimodal_request

Validate if a multimodal request is supported by the specified provider.

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources