Perception runs on your own machine — the client starts it, so there is no endpoint to ping. 135 installs a week from pypi.
Perception for AI agents: media QC asserts, image diff, OCR tiles, video/audio analysis, PDF, 3D.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add perception -- uvx perception-mcp
{
"mcpServers": {
"perception": {
"command": "uvx",
"args": [
"perception-mcp"
]
}
}
}
[mcp_servers.perception]
command = "uvx"
args = ["perception-mcp"]
{
"mcpServers": {
"perception": {
"command": "uvx",
"args": [
"perception-mcp"
]
}
}
}
{
"servers": {
"perception": {
"type": "stdio",
"command": "uvx",
"args": [
"perception-mcp"
]
}
}
}
Local file and media tools: images, PDF, audio, video, OCR, batch and metadata. Runs locally.
Any file → clean Markdown for AI agents: PDF, Office, EPUB, HTML, images, audio/video. Local MCP.
Document conversion and OCR for AI agents: PDF, Office docs, images to text.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI
PDF, image, video, OCR, screenshot, SQL, QR and text tools for agents. No API key, no signup.
AI video, image, speech, voice cloning and avatar generation, plus PDF/audio/video editing tools.
Convert files between 110+ document, image, audio, video, archive and ebook formats from AI agents.
Answers built from our own checks of this server.