Skip to main content
Glama

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

Related MCP server: fal.ai MCP Server

Installation

git clone --recurse-submodules https://github.com/lintyourcode/perception-mcp.git
cd perception-mcp
cp mcp_agent.secrets_template.yaml mcp_agent.secrets.yaml
$EDITOR mcp_agent.secrets.yaml

Usage

Add Perception-MCP to Claude Desktop (v0.3.7+) by adding the following to your claude_desktop_config.json file:

{
  "mcpServers": {
    "perception-mcp": {
      "command": "fastmcp",
      "args": ["run", "perception-mcp", "serve"]
    }
  }
}

Tools

Perception-MCP provides the following tools:

  • query_image: Answer a question about an image's contents

  • query_audio: Answer a question about an audio file's contents

  • query_video: Answer a question about a video's contents

Development

Running tests

uv run pytest -q

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    Enables Claude Desktop and other MCP clients to generate images, videos, music, and audio using Fal.ai models. Supports text-to-image generation, video creation, music composition, text-to-speech, audio transcription, and image enhancement through natural language prompts.
    18
    56
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Provides access to over 600 AI models on fal.ai for generating and editing images, videos, music, and speech directly within Claude. It supports high-performance models like FLUX, Kling, and Whisper for various creative and analytical tasks.
    747 npm
    1
    MIT
  • F
    license
    A
    quality
    D
    maintenance
    Enables local media processing (video/audio) using FFmpeg and FFprobe, allowing frame extraction, audio conversion, and metadata retrieval through natural language.
    5
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables image and video generation from text, image editing, and text-to-video workflows using AI models via OpenRouter and fal.ai.
    MIT