Can the agent fetch the exact mock server endpoints for one of my APIs?

Yes. You can use the `get_doc_url` capability to retrieve both the public facing documentation url and the private mock server endpoint string. Your agent can immediately use this url to simulate requests internally using other modules or tests.

Am I able to update the Blueprint markup completely through the agent?

Absolutely. Instruct your AI agent to fetch the blueprint with `get_api`. Once read into context, prompt the agent to make your desired changes (e.g. 'Add a new POST route for user creation'). Then, instruct it to use `publish_blueprint` to upload the newly revised markdown.

How does the team feature list function mapping work?

Apiary enables collaboration. Utilizing `list_teams`, the agent finds the slugs of your organizations. Then, using `list_team_apis`, it fetches all collaborative APIs available for that precise team. This hierarchy avoids hallucinating random endpoint repositories.

Apiary MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Apiary
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Apiary through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Apiary Assistant",
            instructions=(
                "You help users interact with Apiary. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Apiary"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Apiary MCP Server

Connect your Apiary workspace to your AI agent and take full control of your API design, specification, and validation processes through natural conversation.

The OpenAI Agents SDK auto-discovers all 10 tools from Apiary through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Apiary, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Read API Blueprints — Fetch raw Markdown-based API Blueprints or Swagger files defining endpoints, methods, and parameters without leaving your editor
Publish Documentation — Instantly update your Apiary projects with new markdown code. Mock servers and public documentation sync automatically
Run Dredd Tests — Validate your backend implementation against the blueprint specifications using integrated tests
Team Management — Query team API projects, list team members, and manage your engineering ecosystem intuitively

The Apiary MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Apiary to OpenAI Agents SDK via MCP

Follow these steps to integrate the Apiary MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Apiary

Why Use OpenAI Agents SDK with the Apiary MCP Server

OpenAI Agents SDK provides unique advantages when paired with Apiary through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Apiary + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Apiary MCP Server delivers measurable value.

Automated workflows: build agents that query Apiary, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Apiary, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Apiary tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Apiary to resolve tickets, look up records, and update statuses without human intervention

Apiary MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Apiary to OpenAI Agents SDK via MCP:

get_api

Get the full API Blueprint source code of an Apiary API project

get_doc_url

Get the documentation and mock server URLs for an Apiary API project

get_me

Get the authenticated Apiary user profile

get_team

Get details of a specific Apiary team

list_apis

Apiary is an API design-first platform. List all API projects on Apiary

list_team_apis

List all API projects belonging to a specific Apiary team

list_team_members

List all members of an Apiary team

list_teams

List all teams the authenticated user belongs to on Apiary

publish_blueprint

Use with valid Markdown blueprint/Swagger. Publish (update) the API Blueprint of an Apiary API project

run_tests

Get or run Dredd-style API tests against an Apiary project

Example Prompts for Apiary in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Apiary immediately.

"Get the API Blueprint code for my project named 'payments-gateway'."

"List all team members of the 'frontend-team' in Apiary."

"Update my 'users-api' with this new blueprint code..."

Troubleshooting Apiary MCP Server with OpenAI Agents SDK

Common issues when connecting Apiary to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Apiary + OpenAI Agents SDK FAQ

Common questions about integrating Apiary MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.