How to Use the Dexatel MCP in AutoGen

Q: How do I pass Dexatel tools to an AutoGen AssistantAgent?

Use mcpservertools with StreamableHttpServerParams pointing to your Vinkius URL. The McpToolAdapter automatically converts the tools for the agent.

Deploy multi-agent AutoGen systems that debate, approve, and send Dexatel SMS campaigns.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dexatel MCP to AutoGen

Create your Vinkius account to connect Dexatel 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 Dexatel with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Drive Consensus-Based Dispatch via MCP

AutoGen agents do not just execute commands blindly. You configure a copywriter agent to draft a text and a compliance agent to review it. Once they agree, the execution agent calls `send_sms_message`. If the format is strict, the agents can pull `list_sms_templates` and debate which one fits the user's intent best. This MCP integration turns basic API calls into consensus-driven operations.

Debate Failure Analysis

Troubleshooting telecom APIs requires multiple perspectives. When a text drops, your diagnostic agent pulls `list_failed_sms_deliveries` to grab the logs. A separate engineering agent takes that data, runs `get_sms_message_details` for the specific payload, and argues with the diagnostic agent about why the carrier rejected it. You get a fully reasoned failure report, not just an error code.

Verify Constraints and Sender IDs

Financial constraints stop runaway agents. Before any broadcast begins, a dedicated finance agent executes `get_account_balance_metadata` to check your Dexatel wallet. It then calls `list_authorized_sender_ids` to verify the routing costs. If the math does not work out, the finance agent vetoes the operation and halts the AutoGen group chat immediately.

Setup guide

Set up Dexatel 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 Dexatel 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="Dexatel_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use `mcp_server_tools` with `StreamableHttpServerParams` pointing to your Vinkius URL. The `McpToolAdapter` automatically converts the tools for the agent.

They can. You instantiate the tools once and pass the resulting list to any agent in your group chat that needs API access.

You configure the execution agent with human-in-the-loop settings. It will pause the chat and ask for your terminal input before firing the message.

Yes. The standard HTTP transport handles chunked responses natively, preventing memory crashes when pulling massive address books.

Your underlying API credentials never leave the Vinkius vault. The agents only hold a single endpoint token, communicating over a secure, zero-trust connection.

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