mcpField
P
pixfaro

pixfaro

Remote
pixfaro.comMedia & Design0Updated 9w ago

About pixfaro

pixfaro provides an image-generation MCP server and CLI that use one API and prepaid balance to access image models. It is for MCP-client users and scripts that generate or edit images, and returns hosted image URLs.

Key features

  1. 01Generate and edit images
  2. 02Inspect model prices and latency
  3. 03Check prepaid balance
  4. 04Render template-based cards
  5. 05Upload reusable assets
  6. 06Generate and edit through the CLI

Use cases

  1. 01Generate images through an MCP agent
  2. 02Edit existing images with natural language
  3. 03Create assets in scripts and pipelines
  4. 04Produce template-based cards

MCP support

The MCP server exposes image generation, editing, model listing, and balance tools. Remote connections support OAuth or API-key authentication; some template and asset tools are available only on the remote server.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.pixfaro.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
npm@pixfaro/mcp0.1.2

Tools

8
ParameterTypeRequiredDescription
modelstringNoModel id from list_models
promptstringYesWhat to draw
overlayanyNo
resolutionenumNoOutput tier (default 1K); supported tiers and prices per model are in list_models1K | 2K | 4K
aspect_ratiostringNoe.g. "16:9" (default 1:1). Ratios are per-model — list_models names the ones verified for each. Gemini models take a fixed set (no 4:1 or wider); the budget fal models compute any bounded W:H, so use one of those for banner shapes — up to 4:1 / 1:4, beyond which the derived strip gets too thin to send. Every fal model is 1K-only, so that is the practical bound.

Details

From the project README

Pixfaro MCP — image generation MCP server for every image model

One MCP connection, one prepaid balance, every major image model — Nano Banana, Gemini today, GPT Image next (visible as "coming soon" in list_models). Pixfaro holds the provider accounts, keys, retries and format differences; your agent just asks for an image.

Works with Claude Desktop, Claude Code, Cursor, Windsurf, and any MCP client.

Quickstart — no terminal needed (≈1 minute)

The remote server is the easiest path: paste one URL, sign in with your Pixfaro account in the browser window that opens. No API key in any file.

Claude (claude.ai / Claude Desktop, any plan): Settings → Connectors → Add custom connector → URL https://mcp.pixfaro.com/mcp → sign in. (Team/Enterprise: an org Owner adds it once under Organization settings → Connectors → Custom → Web.)

Cursor: Add to Cursor → — or Cursor Settings → MCP → Add new MCP server (type URL, address https://mcp.pixfaro.com/mcp); Cursor runs the OAuth flow itself.

ChatGPT (Pro/Plus/Business/Edu): Settings → enable Developer mode (connectors live under Plugins since the July 2026 rename, formerly Connectors → Advanced) → add a custom connector with URL https://mcp.pixfaro.com/mcp, OAuth.

Quickstart — command line / config file

  1. Get an API key at pixfaro.com and top up (no subscription).
  2. Add the server to your MCP client config:
{
  "mcpServers": {
    "pixfaro": {
      "command": "npx",
      "args": ["-y", "@pixfaro/mcp"],
      "env": { "PIXFARO_KEY": "pf_live_…" }
    }
  }
}
  1. Ask your agent for an image. That's it.

For Claude Code:

claude mcp add pixfaro -e PIXFARO_KEY=pf_live_… -- npx -y @pixfaro/mcp

Clients that speak streamable HTTP can also take the remote form in the same file — no key, OAuth on first use:

{ "mcpServers": { "pixfaro": { "url": "https://mcp.pixfaro.com/mcp" } } }
``` Clients
without OAuth can pass an API key instead: `Authorization: Bearer pf_live_…`.

## Tools

| Tool | What it does |
|---|---|
| `generate_image` | prompt → hosted image URL (+cost and balance in the reply) |
| `edit_image` | natural-language edit of a previous generation by its `img_…` id |
| `list_models` | models with price, latency, and what each is best for |
| `render_template` | typeset card (quote/post) from a template — $0.02, ~2 s, sharp type · *remote server; npx parity coming in 0.2* |
| `list_templates` | card templates with slots, style axes and exact prices · *remote server* |
| `upload_asset` | upload a PNG/JPEG (≤5 MB) as a reusable asset (e.g. a card avatar) · *remote server* |
| `get_balance` | current prepaid balance |

Replies carry a hosted URL, never base64 — your agent's context stays small.

Both generation tools accept `aspect_ratio` (e.g. `"16:9"`, `"9:16"`). Edits
keep the source image's shape when you omit it — pass one only to reshape.

## CLI

The same package family ships an unscoped CLI for scripts, CI, and pipelines:

```bash
export PIXFARO_KEY=pf_live_…
npx pixfaro gen "a lighthouse at night, minimal flat style" -a 16:9 -o cover.png
npx pixfaro models
npx pixfaro balance
npx pixfaro edit img_8f2a… "make the sky darker" -o v2.png

Environment

VariableMeaning
PIXFARO_KEYyour API key (pf_live_…) — required for everything except models
PIXFARO_API_URLendpoint override (default https://api.pixfaro.com)

What this repo is

The thin open client over the Pixfaro API: the MCP server (@pixfaro/mcp) and the pixfaro CLI share one HTTP client. The balance/provider layer lives behind api.pixfaro.com — this code is intentionally small enough to read before you hand it a key.

MIT © Pixfaro

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.