How to Use the Junip MCP in AutoGen

Q: How do I load Junip tools into my AutoGen setup?

Install autogen-extmcp. Use mcpservertools with your endpoint URL, and pass the resulting list into your AssistantAgent constructor.

Q: Does AutoGen handle the Junip API schemas automatically?

Yes. The McpToolAdapter translates every parameter for endpoints like getaccount and getproduct into a format your agents immediately understand.

Q: What transports work with this MCP integration?

You can use either stdio or StreamableHttpServerParams. Both connect your multi-agent team directly to the backend.

Build autonomous agent teams to debate and manage your Junip reviews with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Junip MCP to AutoGen

Create your Vinkius account to connect Junip 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 Junip with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents debate your review responses.

You don't want a single script firing off replies to angry customers. Create a customer service agent that pulls bad ratings using `list_reviews` and `get_review`. It drafts an initial apology based on the specific complaint. Have a secondary brand-safety agent read the drafted reply. They debate the tone and accuracy before anything gets approved. This multi-agent setup catches mistakes a solo script would miss entirely.

Audit product performance through consensus.

Set up a data analyst agent to run `list_products` and identify items with low aggregate scores. A marketing agent can simultaneously run `list_campaigns` to see if you are actively requesting feedback for those specific items. The agents discuss the findings. If the marketing agent sees a gap, it can flag the specific product ID using `get_product` and recommend a new targeted review campaign to boost the score.

Manage your storefront Q&A automatically via MCP.

Connect your tools to a dedicated Q&A team. One agent monitors `list_questions` for new entries and flags anything that needs immediate attention from the merchant. Another agent uses `list_answers` to check how similar issues were resolved previously. They negotiate the best possible answer based on historical data before notifying your human team to hit send.

Setup guide

Set up Junip 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 Junip 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="Junip_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Junip 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="Junip_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Junip 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 Junip. 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 Junip 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 Junip MCP in AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with your endpoint URL, and pass the resulting list into your `AssistantAgent` constructor.

Yes. The `McpToolAdapter` translates every parameter for endpoints like `get_account` and `get_product` into a format your agents immediately understand.

They share everything in the conversation history. If Agent A calls `get_review`, Agent B reads the exact same JSON output and can debate the findings.

You can use either `stdio` or `StreamableHttpServerParams`. Both connect your multi-agent team directly to the backend.

The tools expose live review and campaign statistics to your local agents. Vinkius handles the authentication layer entirely in memory, ensuring your API tokens and customer data are never written to disk.

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