How to Use the Kontak MCP in AutoGen

Q: How do I register Kontak tools in AutoGen?

Install autogen-extmcp and use the mcpservertools helper to connect this MCP Server with your Vinkius HTTP endpoint. This registers all Kontak tools, including sendoutboundsms, making them available to your AssistantAgent instances.

Q: Can AutoGen agents verify Kontak audit logs?

Yes, a dedicated auditor agent calls getkontakauditlogs to inspect recent system changes. The agent then debates potential security anomalies with your main coordinator agent to flag unusual behavior.

Q: How do AutoGen agents handle Kontak message details?

Your agents use getmessagedetails to retrieve the status of sent texts during their discussion loops. If a message fails, they analyze the error code together and decide whether to retry or escalate the issue.

Q: Can AutoGen agents update Kontak tags?

While agents inspect tags using listkontaktags, they debate and agree on which tags to apply based on customer interactions. This keeps your contact categorization consistent and free from individual agent errors.

Let AutoGen agents debate messaging strategies and coordinate SMS dispatches using the Kontak toolset.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kontak MCP to AutoGen

Create your Vinkius account to connect Kontak 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 Kontak with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate AutoGen agent debates over Kontak SMS campaigns

The `send_outbound_sms` tool is controlled by a multi-agent consensus loop where your AutoGen agents debate the safety and timing of each text. A copywriter agent drafts the message, a compliance agent checks it against `list_kontak_templates`, and a final sender agent triggers the transmission. This collaborative workflow prevents accidental spamming and ensures every message aligns with your brand rules. If the compliance agent objects, the draft goes back for revisions before any external API calls run.

Resolve contact conflicts in AutoGen using this MCP Server

This MCP Server provides `list_kontak_contacts` to help your AutoGen agents resolve duplicate profiles and outdated phone numbers. One agent specializes in scanning the directory while another uses `get_contact_details` to verify the accuracy of the records. They negotiate the best way to merge contacts or update records without manual intervention. Using `list_kontak_tags`, the agents also categorize contacts based on their consensus decisions, keeping your CRM clean.

Manage AutoGen webhooks and rate limits dynamically

The `list_kontak_webhooks` tool lets your AutoGen system monitor active integrations and coordinate automated responses to incoming texts. When a webhook triggers, your agents discuss which team member is best suited to handle the incoming payload. Before sending a reply, the agents check `get_kontak_account_info` to verify your remaining message credits and API limits. This cooperative resource management ensures your automated campaigns never exceed your budget or rate constraints.

Setup guide

Set up Kontak 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 Kontak 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="Kontak_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` and use the `mcp_server_tools` helper to connect this MCP Server with your Vinkius HTTP endpoint. This registers all Kontak tools, including `send_outbound_sms`, making them available to your AssistantAgent instances.

Yes, a dedicated auditor agent calls `get_kontak_audit_logs` to inspect recent system changes. The agent then debates potential security anomalies with your main coordinator agent to flag unusual behavior.

Your agents use `get_message_details` to retrieve the status of sent texts during their discussion loops. If a message fails, they analyze the error code together and decide whether to retry or escalate the issue.

While agents inspect tags using `list_kontak_tags`, they debate and agree on which tags to apply based on customer interactions. This keeps your contact categorization consistent and free from individual agent errors.

Your Kontak API keys and account credentials are encrypted and managed directly by Vinkius. AutoGen agents never see your raw API tokens; they only interact with the tools like `get_kontak_account_info` through secure, sandboxed MCP requests.

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