Connect ngram over MCP

ngram is a native Model Context Protocol server, so Claude, eligible ChatGPT web workspaces and authenticated MCP-aware clients can create videos, check status and read credits as tool calls.

Written By Anish Muppalaneni

Last updated 17 days ago

Read before this

  1. Understand integrations and automation access

Overview

The Model Context Protocol is an open standard for connecting AI assistants to external tools. ngram exposes every public endpoint as an MCP tool with a typed schema the agent reads at connect time, so there is no glue code to write. Use the hosted HTTP endpoint for setup.

Use https://mcp.ngram.com as the remote MCP server URL. Claude connector flows handle auth in the connector UI. In ChatGPT, full create-video actions currently require the web app on Business, Enterprise, or Edu, plus developer-mode and workspace app access; Pro is limited to read/fetch MCP actions. Header-capable clients can authenticate with Authorization: Bearer ngs_…. Every signed-in ngram user can create that bearer credential from Settings → API Keys. Connector flows that handle authentication in their own UI do not require you to paste a key.

Do not paste this JSON into a connector UI that only asks for a server URL. In those clients, add ngram as a custom or remote connector using https://mcp.ngram.com and follow the auth flow the client presents. The hosted endpoint is the supported default for normal setup.

Tool catalog

Every ngram endpoint maps to a discrete tool. The agent reads the typed schema for each at connect time, so it can pick the right one without a docs lookup mid-conversation.

Account

  • get_account — return the authenticated ngram account.
  • get_credits_remaining — return the credit balance and plan.

Catalog

  • list_voices, list_styles, list_aspect_ratios, list_durations — the options a render can use.
  • list_animation_modes, list_scenarios, list_brand_kits — resolve modes, presets and your brand kits.

Videos

  • create_video_from_text and create_video_from_url — start a render from a prompt or a source URL.
  • prepare_video then create_video — preview the resolved settings, then confirm and generate.
  • get_video_status, list_videos, cancel_video — track, list and stop renders.

Images

  • create_image, edit_image, get_image_status, list_images — generate and edit images the same way.

Example prompts

Once connected, just ask in plain language — the agent picks the right tool:

  • "Make a 30-second product teaser for our pricing page and tell me when it's done."
  • "How many credits do I have left?"
  • "List my last five videos and their status."

MCP server FAQ

Which MCP clients are supported?

We test Claude Desktop, Cursor, Cline, Notion AI and eligible ChatGPT apps. Custom clients that support remote MCP servers and compatible authentication use the same tool schema.

Which endpoint should I use?

Use the hosted endpoint at https://mcp.ngram.com. Connector UIs ask for the URL and then handle auth in their own flow; header-capable clients can add a bearer header.

How do I authenticate?

Claude and ChatGPT authenticate inside their connector UI, so those flows do not require you to create or paste an ngram key. For a header-capable hosted HTTP client, every signed-in user can create a key in Settings → API Keys and send it as Authorization: Bearer ngs_….

What tools does the server expose?

Account, catalog, video and image tools — from get_credits_remaining and list_voices to create_video_from_text, get_video_status and create_image. Each has a typed JSON schema the agent reads at connect time.

Are there rate limits?

Yes — the same public-API limits apply. Up to three video jobs can be processing per account at once; the agent surfaces a rate-limit response when you exceed it.

Keep going

Ready to connect ngram?

Use the hosted server URL and complete authentication in your connector. For header-capable custom clients, create a bearer credential in Settings → API Keys.

Review connection steps