How to Use the kvCORE MCP in AutoGen

Q: How do I load kvCORE MCP tools into AutoGen?

Use mcpservertools with StreamableHttpServerParams. Pass that tool list directly into your AssistantAgent constructor.

Q: Do I need to format the JSON for kvCORE updates in AutoGen?

No. The McpToolAdapter translates the conversation into the correct schema for updateleadinfo automatically.

Q: Can AutoGen agents read my kvCORE agent profile?

They can call getagentprofile to understand who owns the current session. This helps them assign tasks accurately during their deliberations.

Let AutoGen agents debate and execute your kvCORE real estate tasks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect kvCORE MCP to AutoGen

Create your Vinkius account to connect kvCORE 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 kvCORE with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent kvCORE Operations

The `search_kvcore_leads` tool gives your AutoGen agents the raw lead IDs they need to start working. You set up a lead-generation agent to find contacts, and a compliance agent to review them. They actually talk to each other. The first agent pulls data, and the second agent argues about whether to call `update_lead_info` based on internal rules. You get consensus-driven updates instead of blind automation.

Debate Agent Priorities via MCP Server

Feed `list_agent_tasks` into your conversation loop to let agents figure out what needs attention. One agent pushes for immediate follow-ups, while another checks `list_lead_activity` to see if the client already responded. This prevents redundant work. The system negotiates the best course of action before anyone touches `create_lead_note`. It's a deliberate approach to managing real estate workflows.

Analyze Marketing and Listings

Give your AutoGen setup access to `list_property_listings` and `list_marketing_campaigns`. A marketing agent looks at active campaigns while a sales agent reviews the property metadata from `get_listing_details`. They cross-reference the data to find gaps in your strategy. The `McpToolAdapter` handles all the schema conversions automatically, letting your agents focus on debating the next move.

Setup guide

Set up kvCORE 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 kvCORE 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="kvCORE_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use `mcp_server_tools` with `StreamableHttpServerParams`. Pass that tool list directly into your `AssistantAgent` constructor.

Yes. You can give the tool list to as many agents as you want. They will share the tools to pull lead details and debate the results.

No. The `McpToolAdapter` translates the conversation into the correct schema for `update_lead_info` automatically.

They can call `get_agent_profile` to understand who owns the current session. This helps them assign tasks accurately during their deliberations.

The MCP server processes raw lead contact notes and phone numbers. Authentication is handled via a single endpoint token, and the execution environment is strictly isolated to prevent any cross-tenant data leakage during agent debates.

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