# Astica AI — how to use (mcp.ai)

Connect your Astica AI account and use 2 tools for artificial intelligence straight from your AI agent. Connect with your own API key. astica ai offers a suite of cognitive intelligence APIs, including computer vision, natural language processing, and voice synthesis, enabling developers to integrate advanced AI capabilities into their applications.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_astica_ai?ms=1787291280000`
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. `astica_ai_analyze_audio`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/astica_ai`
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/astica_ai/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/astica_ai/analyze/audio` — Tool to analyze audio input for transcription. Use when you need to convert an audio URL or Base64 string to text.
  - body: { do_stream?: integer, audio_input: string, low_priority?: integer, model_version?: string }
- `POST https://api.mcp.ai/api/astica_ai/astica/read/text` — Perform OCR (Optical Character Recognition) on an image to extract text. Supports HTTPS image URLs and Base64-encoded images. Returns detected text blocks with bounding box coordinates. Works with pri
  - body: { image_url: string, model_version?: string }

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

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