How to Use the ComboCurve MCP in AutoGen

Enable multi-agent debate and consensus on your data using AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ComboCurve MCP to AutoGen

Create your Vinkius account to connect ComboCurve 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 ComboCurve with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enable multi-agent discourse

Your security agent can use `get_scenario_details` to check for risks while a performance agent analyzes `get_monthly_volumes`. They discuss these findings until they reach a conclusion. This allows for critical review of your production data. The tools provide the raw facts that your agents debate in real time.

Coordinate well data across agents

Use `search_wells_by_name` to locate assets for your team of agents. Once identified, they can divide the work of checking specific well metrics using `get_well`. This distribution of labor speeds up your analysis. Agents verify each other's work by comparing the data they pull from the API.

Manage project scope via consensus

Agents use `list_projects` to define the boundaries of their task. They negotiate which project to focus on based on the metadata returned by these calls. `list_forecasts` serves as the ground truth for their debate. Your agents converge on a strategy by analyzing these figures together.

Setup guide

Set up ComboCurve 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 ComboCurve 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="ComboCurve_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

The agents act as a group, using the server tools to fetch data as needed. They communicate their findings to each other to reach a final decision.

You define which tools each agent has access to in their constructor. This keeps your data usage strictly controlled within the multi-agent conversation.

The server handles all authentication and data transmission through a secure, ephemeral tunnel. Your well and project records are only accessible to the agents currently involved in the discussion.

Agents challenge each other if their results differ. They can re-run the tools to verify the facts, ensuring the final decision is based on accurate API output.

It supports both stdio and HTTP transports. You simply pass the server parameters to the tool adapter to get the agents talking to your API.

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