Modelfy MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Modelfy MCP
An MCP server that lets any AI agent create product photos with Modelfy: Claude, ChatGPT, Codex, Cursor, a bot built on any model API, or your own agent.
https://mcp.modelfy.ai/mcpIt runs on Cloudflare Workers. People connect once and are not asked to sign in again; agents get keys without anyone copying them; and no credit is spent without consent.
What an agent can do
Tool | What it does | Spends credits |
| Balance, plan, price per photo; for live keys the budget and today's spend | no |
| The catalog: people, places, formats, shot types | no |
| Product photos from public image links | no |
| Photos from code (presigned PUT) or from a page a person opens | no |
| Plans a session and returns its exact price and a | no |
| Launches the planned session (needs the quote) | yes |
| Progress and finished photos; can wait until done | no |
| Recent photos; stop a session (unstarted photos are refunded) | refunds |
The server sends its own instructions on connect, tailored to the kind of connection, and every error carries a stable code, a next_step the agent can act on and a docs_url.
Related MCP server: Unsplash MCP
Connecting
How | For | What happens |
OAuth 2.1 (dynamic registration or client ID metadata documents, PKCE) | claude.ai, Claude Desktop, ChatGPT, Claude Code, Codex | The person signs in on the Modelfy web and allows the assistant. Access tokens last an hour; refresh tokens have no fixed end and expire only after 90 idle days. Registered clients are never forgotten. |
Anonymous sandbox key — | Any agent, no account | A free |
Device login (RFC 8628) — | Coding agents and bots that need a real key | The agent shows the person a link; they approve on the Modelfy web (test key, or live key with a budget) and the agent receives the key. |
API key by hand | Anyone who prefers it | Created in the Modelfy account and sent as |
# Try it in ten seconds: a sandbox key, then any MCP client
curl -X POST https://mcp.modelfy.ai/sandbox/keysSpending consent
Every session is planned first (plan_photos): the server keeps the exact plan as a quote, bound to the connection, for 30 minutes. generate_photos launches only a quote, with the quote as the idempotency key, so a retry never charges twice.
OAuth (a person in a chat):
generate_photosneedsuser_confirmed: true, which the instructions tell the agent to set only after the person agrees to the price.Live key (a bot): no confirmation, but each key has a budget per photo session and per UTC day, enforced by the Modelfy API inside the same transaction that reserves the credits.
Test and sandbox keys: never reach a paid route.
Architecture
flowchart LR
A[AI agent] -- "MCP · Bearer token" --> W
subgraph W [Cloudflare Worker]
P[OAuthProvider] --> H[MCP handler]
H --> B{backend}
B --> S[Sandbox]
P --> R[/authorize · /callback · /device · /sandbox/]
K[(KV: grants, clients, quotes, sandbox)]
end
B -- "token + X-Mcp-Secret" --> API[Modelfy API /v2]
R -- consent, device approval --> WEB[Modelfy web]@cloudflare/workers-oauth-provideris the authorization server and checks every token;agents' statelesscreateMcpHandlerserves Streamable HTTP with a freshMcpServerper request.Tools talk to a
PhotoBackend:ApiBackend(the Modelfy API, with the user's token and the Worker's shared secret) orSandboxBackend(the real catalog, everything else canned).The Modelfy API accepts these tokens only from this Worker (shared secret), on an exact list of routes; there is no public REST API.
Development
npm ci --legacy-peer-deps
cp .dev.vars.example .dev.vars
npm run dev # wrangler dev on http://localhost:8787
npm test # Vitest inside the Workers runtime
npm run typecheck && npm run lintStrict TypeScript, no any, no type assertions: every API answer is parsed with zod before it is used.
Deploy
npx wrangler kv namespace create OAUTH_KV --env dev # put the id in wrangler.jsonc
npx wrangler secret put MCP_SERVER_SECRET --env dev # the same value as the API's
npx wrangler secret put SANDBOX_ACCOUNT_KEY --env dev # a test key of the sandbox account
npm run deploy:devLicense
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Create images & video from any MCP agent — 17 models, spend limits, one URL.
Hosted MCP for e-commerce: live product catalog, stock, and pricing for AI agents.
Make product photos and ads, and run Meta and Google Ads campaigns, from your AI app.
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables AI agents to query tenants, browse catalogue items with pricing, pull recent orders, and add products through the MCP tool-calling interface.4MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to search and browse photos, users, collections, and topics, and retrieve photo details, random selections, download tracking URLs, and usage statistics via MCP tools.82 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables agents to list brands, compose prompts, generate or draw assets, check compliance, and manage review workflows through MCP tools.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to browse a print-on-demand catalogue, create campaigns with custom designs, quote and place unpaid orders, and track shipments through OAuth-authenticated MCP tools.12MIT