How to Use the Jiminny MCP in AutoGen

Deploy multi-agent teams that debate and decide based on Jiminny conversation data in AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jiminny MCP to AutoGen

Create your Vinkius account to connect Jiminny 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 Jiminny with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Agent consensus on Jiminny metrics

Create a team where one agent monitors `get_coaching_stats` while another evaluates deal progress. They debate the best coaching approach for a specific rep. This setup allows for nuanced decision-making. You get a balanced conclusion that considers both performance metrics and qualitative call data.

Automated debate using tool outputs

Use the McpToolAdapter to let your agents invoke `get_action_items` as part of their conversation. Agents challenge each other's interpretation of these items. This forces the team to verify information before acting. It reduces errors in your sales strategy by ensuring multiple agents agree on the facts.

Deploy Jiminny tools across agent groups

Integrate the server into your AutoGen workflow using standard HTTP transport. Agents share access to `list_users` and `list_teams` to coordinate their efforts. This creates a unified system where every agent understands the team structure. Your agents work together to map performance across the entire organization.

Setup guide

Set up Jiminny 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 Jiminny 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="Jiminny_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the extension package and provide the server URL to the tool adapter. The adapter automatically handles the schema conversion for the agents. You then pass the tool list to your AssistantAgent constructor.

Yes, you can define a critic agent that reviews the output of `get_call_stats`. If the data looks off, the critic triggers a re-query. It adds a layer of validation to your automated reports.

The framework allows you to set up rules for how agents should negotiate. When they disagree on a coaching strategy, they follow your predefined logic to reach a consensus. It makes the final decision robust.

Yes, the tools are accessible to any agent in your group chat. You can define specific permissions for each agent if you want to limit tool usage. It scales well for complex multi-agent teams.

The server enforces strict endpoint authentication for every request. Only the agents you authorize can see your call transcripts or coaching stats. Your sensitive performance data never leaves your secure infrastructure.

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