How to Use the Kylas MCP in AutoGen

Q: How do I register the Kylas MCP Server tools with my AutoGen agents?

Install the extension with pip install -U "autogen-extmcp". Use mcpservertools with your Vinkius HTTP URL to fetch the MCP tools, then pass that list directly to your AssistantAgent constructor.

Q: Does the schema adapter handle Kylas tool formatting automatically?

Yes, the McpToolAdapter converts the JSON schemas from the MCP server into the format expected by the AutoGen agent. You don't have to write any manual schema conversion code to get started.

Build multi-agent sales debates in AutoGen where specialized agents collaborate to score and update your Kylas CRM leads via MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kylas MCP to AutoGen

Create your Vinkius account to connect Kylas 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 Kylas with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run consensus-driven sales debates in AutoGen

The `get_lead` tool supplies raw prospect data to your debating agents. With this MCP Server, you set up an AutoGen conversation where a qualification agent checks `get_lead` while a security agent reviews the data for compliance. They debate the quality of the prospect before taking action.

Coordinate pipeline reviews across multiple agents

The `list_deals` tool pulls pipeline records for collaborative team analysis. Let your agents run your weekly sales pipeline review. One agent calls `list_deals` to find stalling deals, while another agent analyzes the historical conversion rates. They deliberate on the best next steps for each account.

Automate contact management via agent negotiation

The `list_contacts` tool downloads your customer directory for automated cleaning. Your agents call `list_contacts` to pull the latest customer list and negotiate how to resolve duplicate records or outdated phone numbers. If they find a gap, they call `create_contact` to add the missing details.

Setup guide

Set up Kylas 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 Kylas 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="Kylas_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the extension with `pip install -U "autogen-ext[mcp]"`. Use `mcp_server_tools` with your Vinkius HTTP URL to fetch the MCP tools, then pass that list directly to your `AssistantAgent` constructor.

Yes, you configure your group chat so that a validator agent must approve the payload before another agent calls `create_lead`. This ensures only high-quality, verified data enters your CRM.

The agents use conversational turns to discuss the output of `list_deals`. One agent flags deals with no progress, while another suggests follow-up actions based on the current deal status.

Yes, the `McpToolAdapter` converts the JSON schemas from the MCP server into the format expected by the AutoGen agent. You don't have to write any manual schema conversion code to get started.

Your CRM credentials and active tasks are processed within a secure, ephemeral V8 isolate sandbox that wipes all session data immediately after execution. No customer contact info or task details are ever saved on our platform.

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