photographi-mcp — Claude Code MCP server: technical photo analysis
Runs computer vision on your own machine to score sharpness, focus and exposure. Useful for culling bursts or auditing a folder without uploading anything.
claude mcp add photographi-mcp -- uvx photographi-mcpWhat photographi-mcp 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.
What it helps with
- 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 for the agent
- Is
dog_042.jpgsharp enough to print? - Rank the burst in
cake_burst/and show me the best frame - Move the blurry shots in
vacation/into ajunksubfolder
How to install photographi-mcp
Platform CLI
claude mcp add photographi-mcp -- uvx photographi-mcpuvx runs the command named after the package; if the README names another one, use uvx --from photographi-mcp <command>
Platform CLI
codex mcp add photographi-mcp -- uvx photographi-mcpuvx runs the command named after the package; if the README names another one, use uvx --from photographi-mcp <command>
Config file
{
"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>
Config file
{
"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>
Platform CLI
gemini mcp add photographi-mcp uvx photographi-mcpuvx runs the command named after the package; if the README names another one, use uvx --from photographi-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about photographi-mcp
How do I install photographi-mcp in Claude Code?
Run claude mcp add photographi-mcp -- uvx photographi-mcp. That registers the server at user scope.
What does photographi-mcp do?
It computes technical metrics for photos locally — sharpness, focus, exposure, noise — and lets the agent rank bursts, cull rejects and build palettes from them.
What does the server need to run?
Python 3.10+ and uvx available on PATH. All processing happens on your own hardware; nothing is uploaded.
