How to Use the Apideck MCP in OpenAI Agents SDK

Q: How do I install the Apideck toolset in the OpenAI Agents SDK?

Run pip install openai-agents in your terminal. Instantiate the server using MCPServerStreamableHttp with your Vinkius MCP endpoint, then pass it directly into your Agent constructor using the mcpservers list.

Q: What is the best way to optimize tool-calling performance?

Set cacheToolsList=True in your server configuration. This prevents the SDK from refetching the tool definitions on every single turn, reducing latency for tools like executeproxy.

Run secure CRM integrations and API proxies inside your OpenAI Agents SDK pipelines with zero manual auth.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apideck MCP to OpenAI Agents SDK

Create your Vinkius account to connect Apideck 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 Apideck with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync CRM contacts directly using Apideck MCP Server

The `list_crm_contacts` tool fetches customer records across Salesforce, HubSpot, and other CRM platforms through a unified endpoint. Your OpenAI agents pull live lead lists and contact profiles on demand without writing custom API wrappers for each provider. Under the hood, the OpenAI Agents SDK matches this tool with your schema, letting the model query contacts using natural language. Vinkius secures the connection, passing clean JSON directly to your agent's context window.

Manage user integrations via secure Vault sessions

The `create_vault_session` and `list_vault_connections` tools let your agents configure and track customer integrations on the fly. You run these commands inside the SDK to spin up connection portals where users authorize their own software. When a user needs to disconnect an app, the agent calls `delete_vault_connection` or `get_vault_connection` to clean up. This setup keeps credentials isolated in the Vinkius V8 sandbox, preventing raw API keys from ever touching your agent code.

Route raw downstream API requests on the fly

The `execute_proxy` tool sends direct, authenticated requests to any downstream platform supported by your integration stack. This gives your agent a fallback mechanism when a niche API endpoint falls outside the standard unified schema. The OpenAI SDK traces these execution paths automatically, showing you the exact payload sent through a secure MCP connection. You get full visibility into what the model requested and what the external API returned.

Setup guide

Set up Apideck 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 Apideck tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Apideck 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="Apideck Agent",
            instructions="You have access to Apideck 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 Apideck. 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 Apideck 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 Apideck MCP in OpenAI Agents SDK

Run `pip install openai-agents` in your terminal. Instantiate the server using `MCPServerStreamableHttp` with your Vinkius MCP endpoint, then pass it directly into your Agent constructor using the `mcp_servers` list.

Yes, you can. The OpenAI Agents SDK lets you validate arguments for tools like `list_crm_contacts` before the agent runs them. This stops the model from executing unauthorized queries or passing malformed parameters.

Vinkius manages the MCP server authentication layer, meaning you only need one endpoint token. Your agent calls `list_vault_connections` or `create_vault_session` without needing to store individual client secrets in your environment files.

Set `cacheToolsList=True` in your server configuration. This prevents the SDK from refetching the tool definitions on every single turn, reducing latency for tools like `execute_proxy`.

All session tokens and customer records pass through an ephemeral V8 sandbox. Vinkius operates on a zero-trust model, ensuring that raw vault credentials and contact data are never stored or logged on the host system.

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