# photographi-mcp

Runs computer vision on your own machine to score sharpness, focus and exposure. Useful for culling bursts or auditing a folder without uploading anything.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 5
- Author: prasadabhishek
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/prasadabhishek/photographi-mcp
- Updated: 2026-02-16
- HTML: https://affpapa.org/en/nevibecode/mcp/photographi-mcp

## What it does

photographi-mcp hands an AI agent hard numbers about your photos. Sharpness, focus, exposure, noise, diffraction — the analysis runs on your hardware through the photo-quality-analyzer-core engine, so images never leave the machine.

The server exposes eight tools. `analyze_photo` audits a single frame, `analyze_folder` summarises a directory, `rank_photographs` orders a burst and picks the hero shot, `cull_photographs` moves rejects into a subfolder. Then there is `threshold_cull` for binary sorting at a score cutoff, `get_color_palette` and `get_folder_palettes` for hex extraction, and `get_scene_content` for indexing across 80+ object categories.

Judgements stay technical. A soft or underexposed frame gets flagged as poor even when the blur was deliberate. You need Python 3.10+ and `uvx` on `PATH`; without them the launch command fails. Telemetry is opt-out via `PHOTOGRAPHI_TELEMETRY_DISABLED=1` or the `--disable-telemetry` flag.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add photographi-mcp -- uvx photographi-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from photographi-mcp <command>

### Codex

**Platform CLI**
```bash
codex mcp add photographi-mcp -- uvx photographi-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from photographi-mcp <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "photographi-mcp": {
            "command": "uvx",
            "args": [
                "photographi-mcp"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from photographi-mcp <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "photographi-mcp": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "photographi-mcp"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from photographi-mcp <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add photographi-mcp uvx photographi-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from photographi-mcp <command>

## When to use it
- pick the sharp frames out of a wedding burst
- find the hero shot in a cake bracket
- sweep blurry files into a junk subfolder
- pull a colour palette from a forest shoot
- locate every photo containing a cat or a mountain

## Example prompts
- Is `dog_042.jpg` sharp enough to print?
- Rank the burst in `cake_burst/` and show me the best frame
- Move the blurry shots in `vacation/` into a `junk` subfolder

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107701
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26673
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23283
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9369
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9298

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md