How to Use the journy.io MCP in AutoGen

Q: How do AutoGen agents share journy.io account data during a debate?

The host agent calls getaccount and injects the telemetry payload directly into the group chat context. Other agents in the conversation can then read this data to challenge or validate proposed retention plays.

Q: Can I limit which journy.io tools an AutoGen agent can access?

Yes, you can register only specific tools like listevents with your AssistantAgent, keeping sensitive administrative endpoints hidden from the conversation loop.

Let AutoGen agents debate customer health and coordinate retention plays using live journy.io metrics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect journy.io MCP to AutoGen

Create your Vinkius account to connect journy.io 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 journy.io with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent debates on churn risk via MCP Server

Stop relying on single-agent guesses for customer retention. This server lets you build an AutoGen conversation where a success agent pulls account data via `get_account` while a marketing agent reviews active campaigns through `list_campaigns`. They debate the best path forward, negotiating whether to trigger an automated email or alert an account executive. The conversation converges on a decision backed by real-time customer health scores.

Verify user activity before triggering outreach

Your agents can cross-examine telemetry data via this MCP Server to avoid embarrassing customer emails. One agent checks user segments using `list_segments` to find inactive accounts, while another runs `list_events` to verify if they logged in recently. By discussing these findings in a shared group chat, the agents prevent duplicate triggers. They ensure outreach only occurs when both conditions align with your active growth goals.

Audit custom properties via collaborative agents

Spot inconsistencies in your customer database without writing custom scripts. An auditing agent calls `list_properties` to map out your current metadata schema, comparing it against user profiles fetched via `list_users`. The agent flags missing values or mismatched formats directly to your engineering agent. They work together to clean up your telemetry, using `get_user` to drill down into specific problematic records.

Setup guide

Set up journy.io 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 journy.io 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="journy.io_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

The host agent calls `get_account` and injects the telemetry payload directly into the group chat context. Other agents in the conversation can then read this data to challenge or validate proposed retention plays.

Yes, you can register only specific tools like `list_events` with your AssistantAgent, keeping sensitive administrative endpoints hidden from the conversation loop.

Yes, the MCP adapter automatically translates the JSON schemas from endpoints like `list_goals` into the format required by AutoGen agents.

You configure your endpoint token on Vinkius, which manages the headers for you. Your agents simply call `get_me` to verify they are authenticated before running tasks.

Vinkius handles all authentication at the gateway level. Your actual API key is never exposed to the AutoGen runtime, keeping your SaaS customer profiles and health scores completely isolated.

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