EYES · EARS · PRIVACY SANDBOX
cove-sensory-mcp
COVE-SENSORY-MCP · @MOONLIN1213
connects image, video, sound and music perception to text-only models within local privacy boundaries.
cove-sensory-mcp encapsulates multimodal models into a set of local eyes and ears, allowing text-only companions to read media within strict directory boundaries.
Project address (can be copied to AI):https://github.com/moonlin1213/cove-sensory-mcp
PROJECT INTRO
Project introduction
cove-sensory-mcp provides image, video, audio and music analysis tools for text models through stdio MCP, and routes different media tasks to the corresponding multi-modal agents.
The project emphasizes local privacy sandboxes and strict path boundaries, and is suitable for adding controlled eyes and ears to plain text agents such as Claude Code and Codex.
- Suitable for:A text-based companion or agent that can safely read a variety of media locally.
- Platform:Cross-platform Python and stdio MCP client.
- Usage:Configure the directory and media proxy to allow access, and then register the service on the MCP client.
- License:Apache-2.0。
COMMENTS & FEEDBACK
Comments and Feedback
People who have used this project can come back and tell newcomers: which platform it ran on, whether there were any pitfalls during the installation, and what the actual experience was like. The current version is in guest mode, and you do not need to register an account to leave a message.
The message is waiting for review and will be publicly displayed here after approval.
SOURCE & CREDIT
Atlas is responsible for the introduction and navigation, and the use still returns to the original author.
We do not mirror project files, nor do we intercept author traffic. For installation, download, version updates and the latest instructions, please refer to the project page provided by the original author.
Reading public comments...