findme-mcp

findme-mcp

Enables AI clients to create and manage FindMe Photo wedding galleries, upload photos from local files or URLs, and retrieve analytics and QR codes using natural language.

Category
Visit Server

README

FindMe Photo MCP Server

Official Model Context Protocol server for FindMe Photo — the AI-powered wedding gallery platform.

Drive your FindMe galleries from Claude, ChatGPT Codex, Cursor, and any other MCP-compatible AI client. Create events, upload photos, pull analytics — all in natural language.

What it does

"Create a FindMe event for the Sarah & Mike wedding on April 22, upload every photo in ~/Pictures/Sarah-Mike to it, then show me the QR code."

The AI uses this MCP server to do all three steps in one turn.

Tools

Tool Purpose
create_event Create a new gallery.
list_events List your events (paginated).
get_event Get event details + stats.
update_event Rename, re-date, or change access code.
delete_event Soft-delete with 7-day recovery.
restore_event Un-delete within 7 days.
upload_photos_from_paths Upload local files or folders. Primary upload tool.
upload_photos_from_urls Upload from public URLs (Dropbox, direct Drive links, etc.).
upload_photos_from_drive_folder Import from Google Drive (partial in v1).
get_event_qr PNG QR code pointing to the public gallery.
get_event_analytics Guest visits, unique visitors, downloads, selfie searches.
get_usage Current-month API usage, storage, event totals.

Requirements

Install

The easiest way: let the AI install itself. Paste a prompt, the AI edits its own config. No hidden files.

For a step-by-step walkthrough aimed at non-technical photographers, see the full install guide.

Claude Desktop

Open Claude Desktop, click the Code tab (not Chat), then paste this prompt (replace the key):

Install the FindMe MCP server for me.

- Server name: findme
- Command: npx
- Args: -y findme-mcp
- Env var: FINDME_API_KEY = fm_live_PASTE_YOUR_KEY_HERE

Edit my claude_desktop_config.json under mcpServers, then tell me to fully quit and reopen Claude.

Claude Code (CLI)

claude mcp add findme --scope user --env FINDME_API_KEY=fm_live_xxxxx -- npx -y findme-mcp

ChatGPT Codex

codex mcp add findme --env FINDME_API_KEY=fm_live_xxxxx -- npx -y findme-mcp

Cursor / Windsurf / VS Code / Cline

Use the tool's built-in MCP install UI with:

  • Command: npx
  • Args: -y findme-mcp
  • Env: FINDME_API_KEY=fm_live_xxxxx

ChatGPT web / mobile

Coming soon — requires a hosted MCP endpoint. We're shipping mcp.findme.photo next. In the meantime, use Claude Desktop or Codex.

Any other MCP client

FINDME_API_KEY=fm_live_xxxxx npx findme-mcp

Verify

After restart, you should see findme in your client's tool list (12 tools). Try:

Create a FindMe event called "My First Gallery" for today, then show me the QR code.

Troubleshooting

"MCP server failed to start"

  • Ensure Node.js 18+: node --version
  • First run downloads the package via npx; allow it through your firewall
  • Check the JSON is valid if you edited manually (no trailing commas)

"Your FindMe API key is invalid or has been revoked"

"API access requires Free+, Growth, or Pro"

API access is a paid-tier feature. Upgrade at https://findme.photo/pricing.

Upload fails with "can't find folder" on macOS

macOS privacy protection. Open System Settings → Privacy & Security → Full Disk Access and add your AI client (Claude Desktop, Terminal, etc.). Then quit and reopen.

Upload partially failed

The tool never errors a whole batch for one bad file — it returns a summary showing which files succeeded and which didn't. Ask the AI to retry the failed ones specifically.

Limits

Tier Rate limit Monthly quota
Free+ 10 req/min 500 / month
Growth 60 req/min 10,000 / month
Pro 300 req/min Unlimited

Per file: 50 MB photos, 500 MB videos, 50 files per upload batch.

v1 limitations

  • upload_photos_from_drive_folder requires an existing Drive import created via the findme.photo web UI; the MCP can poll status but not create imports yet.
  • The MCP runs locally on the same machine as your AI client; it only sees files on that machine.

Resources

License

MIT — © 2026 FindMe Photo

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured