mcpField
B
Bannerify

Bannerify

Remote
bannerify.coMedia & Design0Updated 3d ago

About Bannerify

Bannerify provides a hosted MCP server that lets clients create images and PDFs from workspace templates or compose an image from shapes. It is for users who manage designs in Bannerify and requires no local server installation.

Key features

  1. 01List workspace templates
  2. 02Inspect templates and layers
  3. 03Render templates as images
  4. 04Generate PDFs from templates
  5. 05Compose images from shapes
  6. 06OAuth sign-in

Use cases

  1. 01Render a template as a PNG, JPEG, or WebP
  2. 02Create a PDF from an invoice template
  3. 03Compose a banner without using a template

MCP support

The hosted Streamable HTTP MCP server exposes tools for reading workspace templates and project details, rendering images and PDFs, and composing images from shapes. Authentication uses OAuth with dynamic client registration.

Configuration

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

Endpointhttps://api.bannerify.co/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.

Tools

Details

From the project README

Bannerify MCP server

Bannerify runs a remote Model Context Protocol server at https://api.bannerify.co/mcp. Connect it to Claude, Cursor, VS Code, Codex or another MCP client, and the assistant can generate images and PDFs from your Bannerify templates.

This repository holds the setup steps and the registry metadata. The server is hosted: there is nothing to install or run.

  • Transport: Streamable HTTP
  • Auth: OAuth with dynamic client registration. You sign in to Bannerify and choose a workspace on a consent page. You create no API key.
  • Registry name: io.github.bannerify/bannerify

Tools

ToolWhat it does
list_templatesLists the templates in the workspace, optionally with the layers you can change
get_templateReads one template and its layers
get_projectReads the workspace: id, name, plan and creation date
create_imageRenders a template as PNG, JPEG or WebP
create_pdfRenders a template as a PDF and returns a link to it
create_image_from_shapesComposes a one-off image from shapes, with no template

Connect

Claude Code
claude mcp add --transport http bannerify https://api.bannerify.co/mcp

Then run /mcp in Claude Code and sign in.

Claude

Open Customize > Connectors, click + Add, then Add custom connector. Enter Bannerify and https://api.bannerify.co/mcp.

Cursor

.cursor/mcp.json:

{
  "mcpServers": {
    "bannerify": {
      "url": "https://api.bannerify.co/mcp"
    }
  }
}
VS Code

.vscode/mcp.json:

{
  "servers": {
    "bannerify": {
      "type": "http",
      "url": "https://api.bannerify.co/mcp"
    }
  }
}
Codex
codex mcp add bannerify --url https://api.bannerify.co/mcp
codex mcp login bannerify
Other clients

Enter https://api.bannerify.co/mcp, with the HTTP transport and OAuth sign-in.

Example requests

  • "List my Bannerify templates, with the layers of each one."
  • "Create a PNG from my Lifecycle email template. Set the headline to Welcome back."
  • "Create a PDF from my invoice template for Acme Studio."
  • "Design a 1200 by 630 banner with a dark background and the text Launch week."

Limits

A generation from an MCP client counts toward the same plan limits as the REST API. The free plan has 100 images a month. See pricing.

Docs

Support

[email protected]

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.