How to Use the Avaza MCP in AutoGen

Q: How do I configure Avaza tools for AutoGen agents?

Install the autogen-extmcp extension. Use mcpservertools with your Vinkius HTTP endpoint and pass the list to your AssistantAgent.

Q: Can multiple AutoGen agents use the Avaza tools simultaneously?

Yes. You can give the createtask tool to a project manager agent and listinvoices to an accounting agent in the same chat room.

Deploy AutoGen agent teams that debate project scopes and manage Avaza tasks autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Avaza MCP to AutoGen

Create your Vinkius account to connect Avaza 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 Avaza with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen Teams for Avaza Projects

One agent rarely gets complex project planning right. You assign `list_projects` and `get_project` to a researcher agent. That agent pulls the current roadmap and presents it to a manager agent for review. The agents argue about resource allocation before doing anything. A risk agent might flag that a project is behind schedule. They deliberate until they reach a consensus on what needs attention first.

Autonomous Task Management

Executing decisions happens through coordinated tool calls. Once the team agrees on a priority, the executor agent uses the MCP Server to run `create_task`. Another agent immediately runs `list_tasks` to confirm the assignment. Priorities shift constantly in professional services. When a client requests a change, your agents discuss the impact on the timeline. They call `update_task` only after agreeing that the change will not break existing deadlines.

Financial Review Committees

Billing errors cost money. You build a financial committee using this MCP integration where one agent pulls `list_timesheets` and another pulls `list_invoices`. They cross-reference the hours worked against the amounts billed. If the numbers do not match, the agents flag the discrepancy. When everything looks correct, the approval agent fires `create_timesheet` for the new billing cycle. You get built-in peer review for your accounting operations.

Setup guide

Set up Avaza 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 Avaza 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="Avaza_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the autogen-ext[mcp] extension. Use mcp_server_tools with your Vinkius HTTP endpoint and pass the list to your AssistantAgent.

Yes. You can give the create_task tool to a project manager agent and list_invoices to an accounting agent in the same chat room.

The framework converts them automatically. McpToolAdapter translates the JSON schema from the server into native Python function signatures.

Agents check existing state first if you prompt them correctly. They run list_projects to verify a project does not exist before deciding to call create_project.

Nobody outside your local execution environment. The Vinkius sandbox fetches list_timesheets over an encrypted connection, serves it to your agent, and terminates the container immediately.

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