How to Use the Gmelius MCP in AutoGen

Q: Can AutoGen agents collaborate on Gmelius boards?

They can. One agent can list boards using listgmeliusboards while another inspects specific cards using listgmeliusboardcards to negotiate task delegation.

Q: How do AutoGen agents handle email templates?

An agent can call listgmeliustemplates to retrieve approved drafts, then discuss with a reviewer agent whether the selected template fits the customer's specific issue.

Let your AutoGen agents debate, assign, and coordinate shared Gmelius inbox tasks using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gmelius MCP to AutoGen

Create your Vinkius account to connect Gmelius 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 Gmelius with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate shared inbox assignments

Let your agents decide who handles which email. An AutoGen triage agent can fetch unassigned threads using `list_gmelius_conversations` and present them to a specialist agent. They discuss the technical complexity of the message before assigning it. Once they agree on the best owner, they can update the status or trigger a response. This eliminates manual triage queues and ensures every email is evaluated by specialized agent personalities before action is taken.

Debate task prioritization on Kanban boards

Project management isn't always black and white. Your agents can use `list_gmelius_board_cards` to see what is currently on your plates, then debate whether a new customer issue requires an immediate card using `create_gmelius_card`. A support agent might push for high priority, while a developer agent points out current backlog constraints. They negotiate a realistic priority level, keeping your Kanban boards organized without human intervention.

Verify MCP Server status before AutoGen runs

Multi-agent conversations can consume significant tokens, so you don't want them debating over dead connections. You can have a coordinator agent run `check_gmelius_status` to confirm the API is up before starting a complex planning session. If the status check returns an error, the coordinator agent immediately halts the discussion and alerts the human operator, saving you API costs and preventing useless loops.

Setup guide

Set up Gmelius 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 Gmelius 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="Gmelius_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the AutoGen MCP extension to fetch the tools from your Vinkius URL. Pass the resulting tool list directly to your AssistantAgent constructor.

They can. One agent can list boards using `list_gmelius_boards` while another inspects specific cards using `list_gmelius_board_cards` to negotiate task delegation.

An agent can call `list_gmelius_templates` to retrieve approved drafts, then discuss with a reviewer agent whether the selected template fits the customer's specific issue.

Yes, after debating the customer's onboarding status, your agents can call `list_gmelius_sequences` to select and execute the most appropriate automated sequence.

The server only accesses the specific conversations and board cards you request via the API. Vinkius runs the integration in a zero-trust, ephemeral V8 sandbox, ensuring your authentication tokens are never exposed to the debating agents.

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