How to Use the HiDeliver MCP in AutoGen

Q: How do I configure HiDeliver for AutoGen?

Install autogen-extmcp. Pass your endpoint to mcpservertools using StreamableHttpServerParams, then hand the resulting list to your AssistantAgent.

Equip your AutoGen multi-agent systems with HiDeliver to negotiate, schedule, and audit physical dispatches.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HiDeliver MCP to AutoGen

Create your Vinkius account to connect HiDeliver 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 HiDeliver with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate dispatch strategies across AutoGen agents

Autonomous routing requires consensus. You can assign a logistics agent to propose new routes using `create_delivery` while a separate finance agent monitors the budget. Before the pickup logs, the finance agent triggers `get_account_balance`. If the cash threshold is too low, it challenges the logistics agent. They negotiate the priority until both agree on the dispatch.

Audit HiDeliver ledgers with specialized agents

Complex operations need dedicated oversight. You can build a security agent that exclusively runs `list_transactions` to check global ledger events for anomalies. If this agent spots an unusual API key transaction via `get_transaction`, it alerts the group. A manager agent can then intervene and immediately call `cancel_delivery` to stop the mapped trace.

Adjust active route parameters via MCP Server

Conditions change rapidly in physical logistics. When a weather agent reports a delay, it informs the routing agent to pull the current trace using `get_delivery`. The routing agent then calculates a new path and executes `update_delivery`. The entire AutoGen swarm stays aware of the active route parameters without requiring human intervention.

Setup guide

Set up HiDeliver 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 HiDeliver 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="HiDeliver_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install autogen-ext[mcp]. Pass your endpoint to mcp_server_tools using StreamableHttpServerParams, then hand the resulting list to your AssistantAgent.

Yes. If the swarm reaches a consensus that a route is invalid, the designated agent will autonomously fire `cancel_delivery`.

They share the same underlying API connection. One agent can call `get_profile` to verify authenticated account logic and share those details in the group chat.

The McpToolAdapter automatically translates the JSON schemas for `create_delivery` and `update_delivery` into native Python signatures for the agents.

The swarm handles live cash thresholds and ledger events. We isolate these transactions inside a strict V8 Isolate sandbox, ensuring no agent telemetry leaks outside the session.

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