Eden AI

Eden AI MCP Connector for Claude

A+

Access 100+ AI models through a single API — route LLMs, generate embeddings, and execute specialized AI tasks like OCR and translation.

13 tools Official Updated Oct 1, 2026 Official Vinkius Partner

Connect Eden AI to your AI agent and unlock the power of over 100 leading AI providers through a single, unified interface. Orchestrate models from OpenAI, Google, Anthropic, and more without managing multiple API keys.

What you can do

  • LLM Routing — Use chat_completions with smart routing (@edenai) or specify specific provider/model combinations for conversational tasks.
  • Specialized AI Experts — Execute synchronous or asynchronous tasks like OCR, Translation, Image Generation, and Speech-to-Text using universal_ai_sync and universal_ai_async.
  • Embeddings & Search — Convert text into numerical vectors with create_embedding and explore available models via list_embedding_models.
  • File Management — Upload, list, and delete files in Eden AI's persistent storage to provide context for specialized AI features.
  • Usage Monitoring — Keep track of your consumption and available balance with check_credits.

How it works

  1. Subscribe to this server
  2. Enter your Eden AI API Key
  3. Start querying dozens of AI providers from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • AI Developers — quickly test and compare different models (GPT-4, Claude 3, Gemini) without rewriting integration code
  • Automation Engineers — build complex workflows involving OCR, translation, and audio processing using a single API standard
  • Data Scientists — generate embeddings across various providers to find the best fit for RAG or semantic search applications
llm-orchestrationmulti-model-apiocrembeddingsai-routing

13 tools expose this connector's capabilities to your AI agent.

delete_files

Pass an array of file IDs. Delete files from Eden AI storage

chat_completions

Use @edenai for smart routing or specify provider/model. Create a chat completion using Eden AI LLM routing

list_embedding_models

Do not specify any parameters. List available embedding models

list_files

Do not specify any parameters. List all files uploaded to Eden AI

monitor_consumption

Provide start date, end date, and optional step granularity. Monitor API consumption and costs

universal_ai_sync

Model format: feature/subfeature/provider[/model] Execute synchronous expert models (OCR, Translation, Image Gen)

upload_file

Supply both file name and file data. Upload a file to Eden AI persistent storage

check_credits

Do not specify any parameters. Check current Eden AI credit balance

create_custom_token

Set the expiration time if the token should not be permanent. Create a custom API token with specific constraints

create_embedding

Provide the model name and the text input. Convert text into numerical vectors

create_stateful_response

Supply the model, messages, and optionally a previous response ID. Create a stateful chat response that stores history server-side

get_async_job

Pass the required job ID. Get the status and results of an asynchronous Universal AI job

universal_ai_async

g., Speech-to-Text). Use this when the task requires significant processing time. Start an asynchronous expert model job (e.g., Speech-to-Text)

See how to talk to your AI agent using Eden AI.

Create a chat completion using openai/gpt-4o via Eden AI.

I've initiated the chat completion with GPT-4o. The model responded: 'Hello! How can I assist you today with Eden AI's unified interface?'

Generate an image of a futuristic city using image/generation/openai/dall-e-3.

Executing the image generation task... I've successfully generated the image of a futuristic city via DALL-E 3. You can access the result at the provided URL.

Check my current Eden AI credit balance.

I've checked your account. You currently have 45.50 credits remaining in your Eden AI balance.

Simply use the `chat_completions` tool and set the `model` parameter to `@edenai`. This will automatically route your request to the most suitable provider based on performance and cost.

Related Connectors