How to Use the Apiary MCP in AutoGen

Q: How do I register Apiary tools with an AutoGen agent over MCP?

You use the mcpservertools adapter with our hosted endpoint URL. This automatically registers tools like getapi and publishblueprint to your assistant.

Q: Can AutoGen agents run Apiary tests autonomously?

Yes, your QA agent can invoke runtests and analyze the output to verify your endpoints match the blueprint.

Let AutoGen agents debate API designs, run tests, and publish blueprints autonomously without manual intervention.

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 AutoGen

Create your Vinkius account to connect Apiary to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent API design debates with AutoGen

You set up a writer agent to modify schemas and a reviewer agent to inspect them using `get_api`. Design-first API development works best when schemas are thoroughly reviewed. They debate the changes over a conversation thread. Once they reach a consensus, the writer agent uses `publish_blueprint` to push the finalized spec back to your workspace.

Automated QA loops using Dredd tests

A tester agent triggers `run_tests` to execute Dredd validation against your active mock servers. Let your agents handle the testing loop. If the tests fail, the tester agent passes the error logs to a developer agent. The developer agent rewrites the blueprint, updates it, and runs the tests again until they pass.

Coordinate API projects across teams via MCP Server tools

Your AutoGen coordinator agent runs `list_teams` and `list_team_members` to map out your organization. Managing corporate workspaces requires knowing who has access to what. This ensures that before any agent publishes a blueprint, it verifies team membership. Automating this check prevents unauthorized code modifications in shared workspaces.

Setup guide

Set up Apiary MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Apiary tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Apiary_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Apiary data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Apiary_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Apiary data")
    print(result.messages[-1].content)

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 AutoGen

You use the mcp_server_tools adapter with our hosted endpoint URL. This automatically registers tools like `get_api` and `publish_blueprint` to your assistant.

Yes, your QA agent can invoke `run_tests` and analyze the output to verify your endpoints match the blueprint.

The agents use their built-in debate loop to resolve conflicts before calling `publish_blueprint`, ensuring only agreed-upon schemas are published.

It uses Streamable HTTP over SSE, managed entirely by Vinkius, which handles connection pooling and secure authentication.

Yes, Vinkius does not log the payloads of your blueprints or team data. All tool execution data is processed inside zero-trust MCP sandboxes and immediately discarded.

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