How to Use the Desku.io MCP in AutoGen

Q: How do I register Desku.io tools with AutoGen?

Install the extension with pip install -U "autogen-extmcp". Use mcpservertools with StreamableHttpServerParams pointing to your Vinkius MCP endpoint, then pass the resulting tool list directly into your AssistantAgent constructor.

Deploy AutoGen agents to debate and resolve Desku.io tickets through automated multi-agent conversations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Desku.io MCP to AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve tickets via AutoGen multi-agent debate

The `update_ticket` tool acts as the final action after your AutoGen agents debate the best resolution path. One agent can draft the ticket update, while a supervisor agent reviews it to make sure it meets your company's support guidelines. This collaborative process prevents single-agent mistakes. By separating the execution of the ticket update from the initial analysis, you ensure that no support record is changed without a consensus between your agents.

Verify customer details before replying

The `get_customer` tool provides the necessary background data to your customer-facing agent via the MCP Server. Before any reply is sent, a separate verification agent checks the customer's tier to ensure the drafted response matches their service level agreement. If the customer is flagged as high-priority, the agents can escalate the conversation. They do this by calling `list_agents` to find an active human team member and reassigning the ticket immediately.

Draft context-aware conversation replies

The `create_conversation` tool is called by your writer agent to send the final response back to the customer. This only happens after the draft has been cross-referenced with previous ticket history fetched by `list_conversations`. This multi-agent review loop guarantees that the reply addresses the actual history of the issue. Your agents talk to each other to refine the tone and accuracy of the message before posting it back to the thread.

Setup guide

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

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

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

Install the extension with `pip install -U "autogen-ext[mcp]"`. Use `mcp_server_tools` with `StreamableHttpServerParams` pointing to your Vinkius MCP endpoint, then pass the resulting tool list directly into your `AssistantAgent` constructor.

Yes. You can share the tool list across multiple agents. For example, a triage agent can use `list_tickets` to find open issues, while a resolution agent uses `create_conversation` to reply, all within the same conversation thread.

They use conversational consensus. One agent analyzes the ticket with `get_ticket`, proposes a status change, and another agent executes the change using `update_ticket` only after verifying the proposal meets your business rules.

Yes. Vinkius hosts the server and exposes it via a secure, streamable HTTP endpoint. Your AutoGen setup connects directly to this URL, eliminating the need to run local Node or Python environments for the server.

All communications between your AutoGen agents and the Desku.io API go through TLS-encrypted channels. Vinkius runs the MCP Server in an isolated, zero-trust environment where session data is wiped clean the moment the connection closes, leaving no trace of customer emails or ticket text.

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