How to Use the Conflux MCP in OpenAI Agents SDK

Q: How do I set up the Conflux MCP Server with my OpenAI Agents SDK project?

Install the package using pip install openai-agents. Initialize the connection using MCPServerStreamableHttp with your Vinkius endpoint, then pass the server to your Agent constructor. Remember to set cacheToolsList=True to speed up tool discovery.

Query both Conflux spaces directly from your OpenAI Agents SDK system with built-in production guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Conflux to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dual-Space Chain Inspection

This MCP Server exposes tools like `cfx_get_balance` and `eth_get_balance` to bridge the gap between your OpenAI Agents SDK system and Conflux's split architecture. Your agent can read state from Core Space or pull EVM-compatible data from eSpace inside a single execution thread. When building production systems, you can let your OpenAI agent dynamically decide which Conflux space to query based on user intent. The agent calls `cfx_get_status` or `eth_get_block_by_number` to inspect the chain, letting you trace every single RPC call directly on your OpenAI dashboard.

Transaction Prep with OpenAI Agents SDK

Before sending any transaction, your OpenAI Agents SDK system can compute gas costs with tools like `cfx_estimate_gas_and_collateral`. The agent uses this tool or `eth_estimate_gas` for eSpace to get exact numbers before writing to the Conflux network. This prevents failed runs and saves transaction costs on Conflux. The OpenAI agent prepares the execution payload, checks the user's account balance with `cfx_get_account`, and returns the raw transaction data for local signing.

Live Event Tracking and History

Monitoring the Conflux network means pulling logs and receipts in real-time using tools like `cfx_get_logs` inside your OpenAI Agents SDK pipeline. Your agent can scan for specific contract events and confirm execution status with `cfx_get_transaction_receipt`. This MCP setup makes it easy to build automated monitors on Conflux. Instead of polling endpoints manually, your client uses the MCP Server to check the next nonce via `cfx_get_next_nonce` and keeps your application state in sync with the ledger.

Setup guide

Set up Conflux MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Conflux tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Conflux tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Conflux tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Conflux Agent",
            instructions="You have access to Conflux tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package using `pip install openai-agents`. Initialize the connection using `MCPServerStreamableHttp` with your Vinkius endpoint, then pass the server to your Agent constructor. Remember to set `cacheToolsList=True` to speed up tool discovery.

Yes. Since the SDK supports built-in guardrails, you can restrict the agent from calling `cfx_send_transaction` or `eth_send_raw_transaction` without explicit human approval. This keeps your main wallet keys safe from autonomous errors.

The SDK automatically reads the schema exposed by the Conflux MCP Server at startup. Your agent instantly knows how to use all 25 tools, including `cfx_call` and `eth_call`, without you writing any glue code.

Yes, the server exposes both sets of tools. Your agent can call `cfx_get_balance` and `eth_get_balance` back-to-back to compare balances across both networks.

This server only queries public blockchain data like balances, transaction logs, and block details from the Conflux network. Your Vinkius connection runs in a secure, zero-trust sandbox, meaning no private keys or sensitive credentials are ever exposed to the public node.

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