# Contentdrips — how to use (mcp.ai)

Connect your Contentdrips account and use 4 tools for AI content generation straight from your AI agent. Connect with your own API key. Contentdrips generates branded graphics and carousels from reusable templates through an asynchronous rendering API.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_contentdrips?ms=1787295840000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `contentdrips_get_render_job`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/contentdrips`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/contentdrips/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/contentdrips/get/render/job` — Get a Contentdrips render job's current state. Checks status once, fetches export URLs only after completion, and returns failed jobs as terminal data without polling automatically.
  - body: { job_id: string }
- `POST https://api.mcp.ai/api/contentdrips/start/ai/carousel/render` — Generate carousel copy from a topic or supported HTTPS source URL and queue its render. This consumes render quota and may also consume AI credits.
  - body: { output: string, ai_input: string, ai_method: string, template_id: string, content_update?: object[], canvas_background?: object }
- `POST https://api.mcp.ai/api/contentdrips/start/carousel/render` — Queue a manually authored multi-slide carousel as PNG files or a PDF from a known account-owned template. Queuing consumes render quota.
  - body: { output: string, branding?: object, template_id: string, content_update?: object[], carousel_content: object, canvas_background?: object }
- `POST https://api.mcp.ai/api/contentdrips/start/graphic/render` — Queue a PNG or PDF render from a known account-owned Contentdrips template and return the asynchronous job ID. Queuing consumes render quota.
  - body: { output: string, branding?: object, template_id: string, content_update?: object[], canvas_background?: object }

## Example prompts
- "What can I do in Contentdrips?"
- "Show me a summary of my Contentdrips account"

## More
- Page: https://mcp.ai/contentdrips
- Agent spec (llms.txt): https://mcp.ai/contentdrips/llms.txt
- Postman collection: https://mcp.ai/contentdrips/postman.json