PostNitro MCP Server

The PostNitro MCP server lets AI assistants and agents — Claude (Desktop, Code, and Cowork), Cursor, ChatGPT, and any other Model Context Protocol client — create carousels directly. Instead of writing REST API calls, you connect the server once and your AI assistant gets 12 ready-made tools for browsing templates, generating carousels with AI, importing your own content, and retrieving the finished files.

Quick Reference


Server URL	`https://mcp.postnitro.ai/mcp`
Transport	Streamable HTTP
Authentication	`Authorization: Bearer <your-api-key>` header (keys start with `pn-`)
API key	Same key as the Embed API — how to get one
Health check	`GET https://mcp.postnitro.ai/health`
Pricing	Uses your Embed API credits — free plan includes 5 credits/month, no card required

Connecting

Claude Code


claude mcp add --transport http postnitro https://mcp.postnitro.ai/mcp \
  --header "Authorization: Bearer pn-your-api-key-here"

Claude Desktop / JSON configuration

Add the server to your MCP configuration file (for Claude Desktop: claude_desktop_config.json):


{
  "mcpServers": {
    "postnitro": {
      "type": "http",
      "url": "https://mcp.postnitro.ai/mcp",
      "headers": {
        "Authorization": "Bearer pn-your-api-key-here"
      }
    }
  }
}

Cursor

Cursor has native MCP support — add the same JSON configuration above to your Cursor MCP settings.

Other MCP clients

Any client that supports the Streamable HTTP transport can connect using the server URL and the Authorization: Bearer header shown above.

Replace pn-your-api-key-here with your actual API key. The key is the same one used for the Embed API — see Obtaining an API Key.

Available Tools

Creation

Tool	Description
`postnitro_generate_carousel`	Generate a carousel with AI from a topic/text, article URL, or X (Twitter) post URL
`postnitro_import_carousel`	Create a carousel from your own slide content
`postnitro_generate_and_wait`	Generate, poll until complete, and return the output in a single call
`postnitro_import_and_wait`	Import, poll until complete, and return the output in a single call

Discovery

Tool	Description
`postnitro_list_templates`	Browse your design templates with IDs, dimensions, and aspect ratios
`postnitro_list_brands`	List your brand configurations
`postnitro_list_ai_presets`	List your AI presets (platform, tone, audience, language, slide count)
`postnitro_get_import_template`	Get the exact slide structure and rules for importing content

Status & Output

Tool	Description
`postnitro_check_status`	Check generation status (`PENDING`, `COMPLETED`, `FAILED`) and processing logs
`postnitro_get_output`	Retrieve the generated PNG image URLs or PDF document URL

Configuration

Tool	Description
`postnitro_set_defaults`	Save default template, brand, AI preset, and output format so you don’t repeat them on every call
`postnitro_get_defaults`	Retrieve your saved defaults

Typical Agent Workflow

Discover — call postnitro_list_templates, postnitro_list_brands, and postnitro_list_ai_presets to find valid IDs (or postnitro_set_defaults once to skip this in future sessions)
Create — call postnitro_generate_and_wait (AI) or postnitro_import_and_wait (your own content); these handle polling for you
Use the output — the tools return PNG URLs (one per slide) or a single PDF URL, ready to download or publish

For long-running generations or custom polling, use postnitro_generate_carousel / postnitro_import_carousel followed by postnitro_check_status and postnitro_get_output.

Credits

The MCP server consumes the same credits as the Embed API:

Content import: 1 credit per slide
AI generation: 2 credits per slide
Free plan: 5 credits per month (no card required) — paid plans start at $10/month for 250 credits

MCP vs. Embed API vs. Embed SDK

	Best for
MCP Server	AI assistants and agents creating carousels conversationally (Claude, Cursor, custom agents)
Embed API	Programmatic automation — Make.com, Zapier, n8n, cron jobs, custom backends
Embed SDK	Letting your users visually create and edit carousels inside your web app

Support

Email: support@postnitro.ai
Live Chat: Available on postnitro.ai
More details: postnitro.ai/mcp