Perception

io.github.egorthinksPublished by GitHub account egorthinksv0.1.7Updated Oct 25, 2026

Perception for AI agents: media QC asserts, image diff, OCR tiles, video/audio analysis, PDF, 3D.

VerifiedSTDIODesktop onlyMedia & Design

Overview

AI-generated overview

A local MCP server that gives an AI assistant media quality-control and analysis tools for images, video, audio, PDF and 3D content.

What you can do
Run quality-control assertions on media files and compare images to spot differences. Extract text from images using OCR tiles. Analyze video and audio content. Inspect PDF documents and 3D assets.
When to use it
Useful when an assistant needs to check media output for defects, compare image versions, pull text out of pictures, or inspect video, audio, PDF and 3D files as part of a review or production workflow.
Requirements
Runs as a local process on the user's machine, installed from the PyPI package perception-mcp over stdio. Desktop only; no web execution. No authentication, environment variables or headers are declared.
Before you install
It reads local media files, so point it only at content you are comfortable having processed. No credentials or write actions are declared, but confirm what it does with files before relying on it in a pipeline.

Installation

In SourceWeft

  1. Open Perception in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

This repository has no README.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.7LatestSep 16, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.