multimodal-mcp

Name: multimodal-mcp
Author: LinJianKun

Local MCP server that adds multimodal capabilities to text-only models like Codex/DeepSeek, offering tools for image de…

Live

Open / InstallLast updated August 5, 2026

Description

Local MCP server that adds multimodal capabilities to text-only models like Codex/DeepSeek, offering tools for image description, audio transcription, video analysis, image/video generation, and speech synthesis.

Author

LinJianKun

Platform

mcp

Pricing model

free

Capabilities

MCP server

Benchmarks

No benchmark results have been added yet.