# Eden AI — how to use (mcp.ai)

Connect your Eden AI account and use 10 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Eden AI provides one API for accessing and orchestrating AI models across multiple providers for text, image, audio, document, and multimodal workloads.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_eden_ai?ms=1787296020000`
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. `eden_ai_count_anthropic_tokens`).

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

### Endpoints
- `POST https://api.mcp.ai/api/eden_ai/count/anthropic/tokens` — Count input tokens for an Anthropic-format message request before generation, including system content and tool definitions.
  - body: { model: string, tools?: object[], system?: string|object[], messages: object[], tool_choice?: object }
- `POST https://api.mcp.ai/api/eden_ai/create/anthropic/message` — Generate a non-streaming Anthropic-compatible message with content blocks, stop reason, token usage, provider metadata, and Eden AI cost. Each call runs a paid model and consumes Eden AI credits.
  - body: { model: string, top_p?: number, system?: string|object[], messages: object[], fallbacks?: string[], max_tokens?: integer, temperature?: number, stop_sequences?: string[] }
- `POST https://api.mcp.ai/api/eden_ai/create/chat/completion` — Generate a non-streaming OpenAI-compatible chat completion with a current Eden AI model and return its choices, token usage, provider, and cost. Each call runs a paid model and consumes Eden AI credit
  - body: { model: string, messages: object[], fallbacks?: string[], max_tokens?: integer, temperature?: number, response_format?: object, reasoning_effort?: string, router_candidates?: string[] }
- `POST https://api.mcp.ai/api/eden_ai/create/embeddings` — Create embeddings for one text or a batch of texts and return vectors with model, usage, provider, and cost metadata. Each call runs a paid model and consumes Eden AI credits.
  - body: { user?: string, input: string|string[], model: string, dimensions?: integer, encoding_format?: string }
- `POST https://api.mcp.ai/api/eden_ai/create/response` — Create or continue a synchronous OpenAI Responses-compatible text response, stored by default for later retrieval, and return its ID, structured output, text, usage, provider, and cost.
  - body: { input?: string, model: string, store?: boolean, fallbacks?: string[], temperature?: number, instructions?: string, max_output_tokens?: integer, previous_response_id?: string }
- `POST https://api.mcp.ai/api/eden_ai/discover/capabilities` — Find current Eden AI models or inspect Universal AI feature schemas, providers, pricing, and regions before an execution call.
  - body: { query?: string, region?: string, feature?: string, provider?: string, model_type?: string, subfeature?: string, max_results?: integer, discovery_type?: string }
- `POST https://api.mcp.ai/api/eden_ai/get/cost/overview` — Return current account credits and, when a date range is supplied, aggregated consumption filtered by provider or subfeature.
  - body: { end_date?: string, provider?: string, start_date?: string, subfeature?: string, aggregation?: string }
- `POST https://api.mcp.ai/api/eden_ai/get/response` — Retrieve a previously stored Responses API object by ID, including its status, text output, structured output, usage, and canonical model.
  - body: { response_id: string }
- `POST https://api.mcp.ai/api/eden_ai/moderate/text` — Classify one text or a batch of texts for safety categories and return flags, category scores, applied input types, provider, and cost. Each call runs a paid model and consumes Eden AI credits.
  - body: { input: string|string[], model?: string }
- `POST https://api.mcp.ai/api/eden_ai/run/universal/ai` — Run one synchronous Eden AI Universal AI feature using a current model and feature-specific input. Call DISCOVER_CAPABILITIES first for the exact model ID and runtime input schema. Returns normalized 
  - body: { input: object, model: string, fallbacks?: string[], provider_params?: object, show_original_response?: boolean }

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

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