How to Use the Conflux MCP in AutoGen

Q: How do I configure the Conflux MCP Server in AutoGen?

Install the extension using pip install -U "autogen-extmcp". Then, load the MCP tools using mcpservertools with your Vinkius HTTP URL, and pass the adapter list directly to your AssistantAgent.

Q: Can AutoGen agents debate gas costs on Conflux?

Yes, you can set up one agent to call cfxestimategasandcollateral and another to analyze the current gas market. They will negotiate the optimal gas price before initiating a transaction.

Let your AutoGen agents debate and verify Conflux blockchain transactions before sending them.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Conflux MCP to AutoGen

Create your Vinkius account to connect Conflux 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 Conflux with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent consensus for blockchain transactions

The Conflux MCP Server exposes `cfx_send_transaction` and `eth_send_raw_transaction` to submit transactions to the network. In an AutoGen setup, you can have a security agent inspect the transaction payload before a sender agent submits it. This multi-agent debate prevents costly mistakes on the blockchain. One agent can estimate the gas while another reviews the contract call, ensuring consensus before any real assets move.

Automated gas and balance validation with AutoGen

Checking transaction feasibility is powered by `cfx_get_balance` and `cfx_estimate_gas_and_collateral` to ensure accounts have sufficient funds. Your AutoGen agents can run these checks in parallel to verify a transaction's viability. If the balance is too low, the monitoring agent can flag the issue and pause the workflow. This automated validation loop keeps your deployment pipelines running smoothly without manual intervention.

Real-time block and epoch monitoring

Monitoring network state relies on `cfx_get_status` and `cfx_get_best_block_hash` to track the tip of the blockchain. Your agents can coordinate to watch for new blocks and process incoming transactions as they land. By using this MCP Server, one agent can watch the epoch number using `cfx_get_block_by_epoch_number` while another processes the receipts. This cooperative approach makes handling high-throughput blockchain data highly efficient.

Setup guide

Set up Conflux 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 Conflux 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="Conflux_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the extension using `pip install -U "autogen-ext[mcp]"`. Then, load the MCP tools using `mcp_server_tools` with your Vinkius HTTP URL, and pass the adapter list directly to your `AssistantAgent`.

Yes, you can set up one agent to call `cfx_estimate_gas_and_collateral` and another to analyze the current gas market. They will negotiate the optimal gas price before initiating a transaction.

Your agents can prepare transaction payloads locally, and then use `cfx_send_raw_transaction` or `eth_send_raw_transaction` to broadcast the signed payload to the network once consensus is reached.

Yes, the Vinkius hosting environment supports stateless execution, allowing multiple agent conversations to query the network concurrently without state collisions.

The server only interacts with public on-chain data like block hashes, transaction receipts, and epoch numbers. Private keys are never processed by the server; all signing happens on your local client before broadcasting raw transactions.

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