Perception-MCP
A lightweight Model Context Protocol (MCP) server that lets you ask any question about an image, audio, or video file and returns an answer powered by state-of-the-art multimodal models served through fal.ai.
Prerequisites
Installation
Usage
Add Perception-MCP to Claude Desktop (v0.3.7+) by adding the following to your claude_desktop_config.json
file:
Development
Running the test suite
The project uses pytest
with pytest-asyncio
to handle FastMCP’s async helpers.
All tests should pass, verifying that the server registers its tools and that the current stubs raise NotImplementedError
until implemented.
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Enables asking questions about image, audio, or video files using state-of-the-art multimodal models. Powered by fal.ai for advanced media analysis and understanding capabilities.
Related MCP Servers
- -securityAlicense-qualityA powerful server that integrates the Moondream vision model to enable advanced image analysis, including captioning, object detection, and visual question answering, through the Model Context Protocol, compatible with AI assistants like Claude and Cline.Last updated -17JavaScriptApache 2.0
- AsecurityAlicenseAqualityEnables querying documents through a Langflow backend using natural language questions, providing an interface to interact with Langflow document Q\&A flows.Last updated -114JavaScriptMIT License
- -securityFlicense-qualityInterfaces with the Perplexity AI API to provide advanced question answering capabilities through the standardized Model Context Protocol, supporting multiple Perplexity models.Last updated -JavaScript
- -securityFlicense-qualityProvides chat and image analysis capabilities through OpenRouter.ai's diverse model ecosystem, enabling both text conversations and powerful multimodal image processing with various AI models.Last updated -168TypeScript