How to Use the Eden AI MCP in OpenAI Agents SDK

Q: How do I connect Eden AI to the OpenAI Agents SDK?

Install the openai-agents package. Create an MCPServerStreamableHttp instance with your Vinkius endpoint URL. Pass it in the mcpservers list when initializing your Agent.

Q: Can the OpenAI Agents SDK track my Eden AI API costs?

Yes. Your agent can execute the getapiusagestatistics tool to pull raw cost data. You can then use OpenAI's built-in guardrails to halt execution if spending exceeds your limits.

Q: What happens if an Eden AI provider fails during an OpenAI Agents SDK run?

Your agent can catch the error and invoke listaiproviders to find an alternative. It then routes the request to a fallback vendor, keeping the production pipeline moving.

Q: How do I list available models in my agent?

Call the listallllmmodels tool. It returns every large language model accessible through your unified API account.

Q: Does this MCP server expose my workflow data to OpenAI?

Only the specific metadata requested via getworkflowconfiguration transmits to the client. The V8 Isolate Sandbox ensures your Eden AI API keys and raw workflow execution payloads remain isolated from the external agent environment.

Connect OpenAI Agents SDK to Eden AI to manage multi-provider workflows and track API costs in production.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Eden AI MCP to OpenAI Agents SDK

Create your Vinkius account to connect Eden AI to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Eden AI with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route multi-provider pipelines via MCP Server

Your agent calls `list_ai_providers` to find alternative vendors when a primary model hits a rate limit. Production systems need fallback options. It pulls active vendor lists instantly. You build the logic, and the agent switches providers without human intervention. The agent uses `list_ai_workflows` and `get_workflow_configuration` to read existing setup states before executing them. Managing complex pipelines requires visibility. It checks what steps are defined. This keeps your multi-agent handoffs grounded in actual configuration data instead of guessing.

Track tokens and pricing automatically

Your agent runs `get_api_usage_statistics` to pull raw token consumption metrics directly from your account. Multi-provider setups burn through credits fast if you ignore them. It aggregates the data so your dashboard reflects reality. By calling `get_ai_feature_pricing`, the agent calculates the exact cost matrix for a specific feature across different vendors. Cost prediction matters before execution. You set the budget constraint, and the agent picks the cheapest model that fits the requirement.

Audit available models and features

Your agent triggers `list_all_llm_models` to fetch the current roster of available models through the unified API. The API space changes weekly. Instead of hardcoding model names, your system knows exactly what is available at runtime. The `get_eden_ai_metadata` tool pulls your current credit balance and version metadata to check account health. If credits run low, your system can alert the DevOps channel before tasks start failing.

Setup guide

Set up Eden AI MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Eden AI tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Eden AI tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Eden AI tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Eden AI Agent",
            instructions="You have access to Eden AI tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Eden AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Eden AI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Eden AI MCP in OpenAI Agents SDK

Install the `openai-agents` package. Create an `MCPServerStreamableHttp` instance with your Vinkius endpoint URL. Pass it in the `mcp_servers` list when initializing your Agent.

Yes. Your agent can execute the `get_api_usage_statistics` tool to pull raw cost data. You can then use OpenAI's built-in guardrails to halt execution if spending exceeds your limits.

Your agent can catch the error and invoke `list_ai_providers` to find an alternative. It then routes the request to a fallback vendor, keeping the production pipeline moving.

Call the `list_all_llm_models` tool. It returns every large language model accessible through your unified API account.

Only the specific metadata requested via `get_workflow_configuration` transmits to the client. The V8 Isolate Sandbox ensures your Eden AI API keys and raw workflow execution payloads remain isolated from the external agent environment.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript