Photographi Mcp

io.github.prasadabhishekPublished by GitHub account prasadabhishekv0.2.6Updated Oct 28, 2026

Visual Intelligence Command Center: A Local Computer Vision Engine for Photo Libraries

VerifiedSTDIODesktop onlyFiles & StorageMedia & Design

Overview

AI-generated overview

Local computer-vision MCP server that lets an assistant audit, rank, cull and index photos in local folders by technical quality.

What you can do
  • Analyze a single photo or a whole folder for sharpness, focus, exposure, composition and quality alerts
  • Rank photographs, for example within a burst, to find the technically best frame
  • Cull photos into a subfolder or split keepers by a score threshold
  • Extract dominant color palettes from one image or a whole folder
  • Index scene content by object category to find photos containing a given subject
When to use it
Useful when you want an assistant to triage a local photo library: picking the sharpest frame from a burst, sorting out blurry or badly exposed shots, or building a quick overview of a folder's quality and colors. It is meant for objective technical metrics, not aesthetic judgement.
Requirements
Runs as a local process, installed from PyPI and typically launched with uvx, so a Python environment with uv is needed. Analysis runs on the user's own hardware. No accounts, API keys or headers are declared.
Before you install
Culling tools move photos into a subfolder, so files in the chosen folders are changed; review targets before running. The README states anonymized aggregate telemetry is collected by default, with no filenames, paths or EXIF, and can be turned off with the PHOTOGRAPHI_TELEMETRY_DISABLED environment variable or a disable flag. Judgements are technical only and may flag artistically intentional images as poor.

Installation

In SourceWeft

  1. Open Photographi Mcp 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

photographi-mcp

Fast, private, and grounded technical photo analysis for AI applications.

photographi-mcp is an MCP server that enables AI models and LLM-powered tools to perform technical analysis on local photo libraries. It runs computer vision models directly on your hardware (powered by photo-quality-analyzer-core) to evaluate sharpness, focus, and exposure—enabling capabilities like automated culling, burst ranking, and metadata indexing without requiring a cloud upload.

⚡ Why photographi?

  • Technical First: Purpose-built for objective metrics (sharpness, lighting, focus). It provides technical data for evaluating image quality.
  • Token Efficient: Save model context by pre-filtering technical metadata locally. Only the most relevant insights are sent to the AI application, keeping sessions fast and lean.
  • Privacy First: All analysis happens 100% locally on your machine.
  • Low Latency: Built for efficient processing, allowing for rapid ranking and technical feedback on local photo folders.

👁️ What It Analyzes

  • Smart Focus: Detects subjects and verifies they're sharp
  • Exposure: Catches blown highlights and blocked shadows
  • Gear-Aware: Knows your lens's sweet spot for optimal sharpness
  • Composition: Evaluates framing and subject placement
  • Quality Alerts: Flags motion blur, diffraction, high ISO noise

[!NOTE] Technical vs. Artistic: This tool is strictly objective. It evaluates photos based on technical metrics and computer vision (sharpness, exposure, noise, etc.). It does not understand artistic intent, aesthetics, or "vibe." A blurry, underexposed photo may be an artistic masterpiece, but photographi will correctly flag it as technically poor.

For the science and math behind it, see the Technical Documentation.

📸 See It In Action

Here are real examples from actual photo analysis:

Example 1: Excellent Photo

[Best Shot]

json
{  "overallConfidence": 0.89,  "judgement": "Excellent",  "keyMetrics": {    "sharpness": 0.94,    "exposure": 0.87,    "composition": 0.85  }}

Verdict: Tack sharp on subject, well exposed, strong composition.

Example 2: Poor Photo

[Worst Shot]

json
{  "overallConfidence": 0.20,  "judgement": "Very Poor",  "keyMetrics": {    "sharpness": 0.30,    "focus": 0.07,    "exposure": 0.0  }}

Verdict: Missed focus on subject, severe underexposure/black clipping, and excessive headroom.

🛠️ Tools (MCP)

photographi-mcp enables AI models to perform deep technical audits through these standardized tools:

ToolAI "Intent" ExampleAction / Insight Provided
analyze_photo"Is this dog photo sharp enough for a print?"Full technical audit of sharpness, focus, and lighting.
analyze_folder"How's the overall quality of my 'Vacation' folder?"Statistical summary identifying the best/worst image groups.
rank_photographs"Find the best shot in this burst of the cake."Ranks files by technical perfection to find the "hero" frame.
cull_photographs"Move all the blurry photos to a junk folder."Automatically cleans up failed shots into a subfolder.
threshold_cull"Strictly separate keepers using a score of 0.7."Binary sorting to isolate professional-grade assets.
get_color_palette"What colors are in this sunset for my website?"Extracts hexadecimal codes for dominant image aesthetics.
get_folder_palettes"Generate a moodboard from my 'Forest' shoot."Batch color extraction for an entire folder.
get_scene_content"Which photos contain a 'cat' or 'mountain'?"Rapid content indexing based on 80+ object categories.

Full API Reference

🚀 Get Started

Claude CLI (Fastest)

bash
claude mcp add --scope user photographi uvx photographi-mcp

Claude Desktop (macOS)

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

json
{  "mcpServers": {    "photographi": {      "command": "uvx",      "args": ["photographi-mcp"]    }  }}

GitHub Copilot CLI

Add to ~/.config/github-copilot/config.json:

json
{  "mcp_servers": {    "photographi": {      "command": "uvx",      "args": ["photographi-mcp"]    }  }}

🔒 Privacy & Telemetry

photographi is built on a Privacy-First philosophy.

  • Anonymized Aggregates Only: We never collect filenames, paths, or EXIF data.
  • Total Transparency: Audit our collection logic directly in analytics.py.
  • Opt-Out: Set the environment variable PHOTOGRAPHI_TELEMETRY_DISABLED=1 or use the --disable-telemetry flag.

📖 Documentation

[License: MIT] [MCP Protocol] [Image] [Python 3.10+]

Built with ❤️ for photographers

Source: README.md at commit 9a8fbb8

Tools

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

Version history

1
  1. v0.2.6LatestSep 16, 2026

Score

50% 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
  • License10 pts