How to Use the Apiary MCP in OpenAI Agents SDK

Q: How do I connect Apiary to my OpenAI Agents SDK pipeline?

Install the SDK and configure the MCPServerStreamableHttp client with your Vinkius endpoint. Pass this server instance in the mcpservers list when initializing your agent. The system automatically discovers all ten tools.

Q: Does the OpenAI Agents SDK cache the Apiary tool definitions?

Yes, setting cacheToolsList=True during initialization caches the tool schemas. This prevents redundant network requests to Vinkius, keeping your agent execution loops fast.

Q: Can an agent trigger Dredd tests through this setup?

The agent uses the runtests tool to run your API test suites. It receives the real-time test results directly back into its context window to determine if the API matches the blueprint.

Build production-grade agents that safely manage your API blueprints using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apiary MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy Apiary tools inside OpenAI Agents SDK

Your autonomous agents need access to API designs without breaking production. By loading this MCP Server into your agent array, your system automatically discovers operations like `list_apis` and `get_api`. This lets your agent inspect raw API Blueprint files directly within your established safety boundaries. You configure this by passing the MCP Server parameters directly into the agent constructor. Turn on `cacheToolsList` to keep agent startup times under a second while preserving your OpenAI dashboard tracing.

Automate blueprint updates with guardrails

Writing API designs by hand is slow and error-prone. Let your agent draft modifications, run validations, and call `publish_blueprint` to push updates directly to your teams. By using this MCP Server, you can intercept these calls to verify schemas before they touch live mock servers. The agent handles the tedious work of structuring the Markdown or Swagger payload. If the update fails, the agent reads the error, corrects the blueprint, and retries the publish call automatically.

Verify API compliance via automated test runs

Stop shipping broken endpoints. Your agent can execute `run_tests` to trigger Dredd-style validation suites against your Apiary mock servers or staging environments. It analyzes the raw test outputs to pinpoint exactly where your implementation diverges from the published blueprint. This MCP setup keeps your documentation perfectly aligned with actual code. When tests fail, the agent can hand off the task to a specialized debugging agent to write a fix.

Setup guide

Set up Apiary 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 Apiary tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK and configure the `MCPServerStreamableHttp` client with your Vinkius endpoint. Pass this server instance in the `mcp_servers` list when initializing your agent. The system automatically discovers all ten tools.

Yes, you control access via the API token you supply to the MCP Server. The agent can only execute `list_team_apis` and `list_teams` for the specific organizations authorized by that token.

Yes, setting `cacheToolsList=True` during initialization caches the tool schemas. This prevents redundant network requests to Vinkius, keeping your agent execution loops fast.

The agent uses the `run_tests` tool to run your API test suites. It receives the real-time test results directly back into its context window to determine if the API matches the blueprint.

Your API blueprints and team data run inside an isolated, ephemeral V8 sandbox on Vinkius. This MCP Server does not store raw credentials or blueprint drafts, and all transport traffic is encrypted end-to-end.

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