Yes, Phototology is free to use.

How do I install Phototology?

Phototology is a local plugin. Install it using npm package: @phototology/mcp and add the generated configuration snippet to your AI app's MCP config file. Then restart your AI app.

Is Phototology safe to use?

Yes. Phototology passed MCP Marketplace's automated security scan with a score of 9.7/10 (low risk). Every server on MCP Marketplace is security-scanned before it's listed; see the full security report on this page for the findings and permissions.

What credentials does Phototology need?

Phototology requires the following credentials or environment variables: PHOTOTOLOGY_API_KEY, PHOTOTOLOGY_BASE_URL, PHOTOTOLOGY_MCP_NO_TELEMETRY, DO_NOT_TRACK, PHOTOTOLOGY_MCP_ALLOWED_DIRS. You can find setup instructions on the server detail page.

What AI apps work with Phototology?

Phototology uses the Model Context Protocol (MCP) and works with any MCP-compatible AI app, including Claude, ChatGPT / Codex, Gemini, Copilot, Cursor, and more.

Back to Browse

Phototology MCP Server

by Phototology Ai

Developer ToolsLow Risk9.7MCP RegistryLocal

Free

Server data from the Official MCP Registry

Persistent memory for visual intelligence. A photo registry: analyze once, look up free after that.

About

Persistent memory for visual intelligence. A photo registry: analyze once, look up free after that.

Security Report

9.7

Low Risk9.7Low Risk

Valid MCP server (3 strong, 3 medium validity signals). No known CVEs in dependencies. ⚠️ Package registry links to a different repository than scanned source. Imported from the Official MCP Registry. 1 finding(s) downgraded by scanner intelligence.

15 files analyzed · 1 issue found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

env_vars

Check that this permission is expected for this type of plugin.

file_system

Check that this permission is expected for this type of plugin.

HTTP Network Access

Connects to external APIs or services over the internet.

What You'll Need

Set these up before or after installing:

Your Phototology API key (pt_live_... for production, pt_test_... for the free fixture sandbox). Get one at https://phototology.com/dashboard. New accounts include 1,000 free credits on email verification.Required

Environment variable: PHOTOTOLOGY_API_KEY

Override the API base URL. Defaults to https://api.phototology.com. Used for local development against phototology-api.Optional

Environment variable: PHOTOTOLOGY_BASE_URL

Set to 1 to disable anonymous telemetry: the editor name and version, the package version, and per tool call the tool name, success, duration, error code and counts. Never image content, file paths, tool inputs or outputs, or conversation text.Optional

Environment variable: PHOTOTOLOGY_MCP_NO_TELEMETRY

Set to 1 to disable telemetry. Same effect as PHOTOTOLOGY_MCP_NO_TELEMETRY; follows the cross-tool convention many CLIs honor.Optional

Environment variable: DO_NOT_TRACK

Folders the server may read photos from and write enriched copies to, separated by : (; on Windows). Unset means any local path. Paths are checked after symlinks are resolved.Optional

Environment variable: PHOTOTOLOGY_MCP_ALLOWED_DIRS

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "com-phototology-mcp": {
      "env": {
        "DO_NOT_TRACK": "your-do-not-track-here",
        "PHOTOTOLOGY_API_KEY": "your-phototology-api-key-here",
        "PHOTOTOLOGY_BASE_URL": "your-phototology-base-url-here",
        "PHOTOTOLOGY_MCP_ALLOWED_DIRS": "your-phototology-mcp-allowed-dirs-here",
        "PHOTOTOLOGY_MCP_NO_TELEMETRY": "your-phototology-mcp-no-telemetry-here"
      },
      "args": [
        "-y",
        "@phototology/mcp"
      ],
      "command": "npx"
    }
  }
}

Documentation

View on GitHub

From the project's GitHub README.

Phototology

Persistent memory for visual intelligence.

phototology.com · npm scope: @phototology

Phototology is a visual-intelligence platform that analyzes a photo once and remembers the result forever, keyed by perceptual hash. Re-running any analysis on the same image — by any client, on any future day — returns the cached structured result for free.

This repository is the public source for the three npm packages that surround the platform. The Phototology API itself runs as a hosted service at api.phototology.com.

Packages

Package	Purpose	npm
`@phototology/sdk`	TypeScript client SDK	npmjs.com/package/@phototology/sdk
`@phototology/mcp`	Model Context Protocol server for Claude Code, Cursor, VS Code, and other AI coding assistants	npmjs.com/package/@phototology/mcp
`phototology`	Unscoped flagship placeholder; reserves the bare name and points to the working packages	npmjs.com/package/phototology

Each package has its own README and CHANGELOG in its directory.

Quick start

Use the MCP in Claude Code, Cursor, or VS Code (no API key needed for the test sandbox):

npx -y @phototology/mcp

For a real API key, sign up at phototology.com.

Use the SDK programmatically:

npm install @phototology/sdk

import { PhototologyClient } from '@phototology/sdk';

const client = new PhototologyClient({ apiKey: process.env.PHOTOTOLOGY_API_KEY });
const result = await client.analyze({
  imageUrl: 'https://example.com/photo.jpg',
  lenses: ['dating', 'people', 'location'],
});
console.log(result);

How it's built

This repo is a public mirror of the package folders from a private monorepo. Changes flow one way: upstream → here. Issues and pull requests are welcome; fixes are applied upstream and synced back.

CI runs on every push and pull request: a frozen install from the committed pnpm-lock.yaml, typecheck, tests, build, a check that each npm tarball contains exactly the files in its pack-manifest.json, gitleaks, and the public-surface guard.
Releases are published from this repo by .github/workflows/release.yml, to npm with provenance (trusted publishing, no npm token), with a GitHub release carrying an SBOM, and to the MCP Registry.

What is (and isn't) in this repo

Only what an explicit allowlist (public-surface.allowlist) permits is synced here, read from git, and every sync is checked by scripts/public-surface/check.mjs before it is pushed. That check rejects secrets, any customer or personal data (including derived hashes, EXIF, filenames and IDs), production-derived fixtures, internal docs and agent notes, infrastructure names and private paths. Test fixtures are synthetic or public-domain (see each tests/fixtures/SOURCES.md).

Found something here that shouldn't be public? Please report it privately as described in packages/mcp/SECURITY.md.

License

MIT — see LICENSE. Each package also carries its own copy of the MIT license in its directory.

Reviews

No reviews yet

Be the first to review this server!

4.8

Local

MCP Marketplace

Free

by mcp-marketplace · Developer Tools

Search and install MCP servers from inside your AI client.