How do I get my AntChain Access Key and Secret Key?

Log in to the AntChain BaaS console, navigate to the API Management or Developer Center section, and create a new API credential pair. You'll receive an Access Key (public identifier) and a Secret Key (used for HMAC-SHA256 signature generation). The Secret Key is shown only once — save it immediately. These credentials authenticate all your API requests.

What's the difference between querying a block and querying a transaction?

A block query returns information about the container itself — block height, hash, timestamp, transaction count, and the previous block hash. A transaction query returns details about a specific operation within a block — sender/receiver addresses, gas used, execution status, return values, and whether the transaction succeeded or reverted. Use blocks to explore the chain structure, and transactions to verify individual operations.

Can I deploy smart contracts through this MCP server?

Yes! Use the `deploy_contract` tool to upload and deploy compiled smart contract bytecode to your AntChain network. You'll need the contract bytecode (in hex format), a name for the contract, and optionally the ABI for future interactions. After deployment, you can invoke contract methods using the `invoke_contract` tool. Make sure your account has sufficient permissions and balance for deployment.

AntChain MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: AntChain
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect AntChain through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="AntChain Assistant",
            instructions=(
                "You help users interact with AntChain. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from AntChain"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About AntChain MCP Server

Connect your AntChain (蚂蚁链) BaaS platform account to any AI agent and gain complete visibility and control over your enterprise blockchain operations through natural conversation. AntChain is Alibaba Group's blockchain-as-a-service platform, designed for consortium chains, enterprise smart contracts, and secure decentralized applications.

The OpenAI Agents SDK auto-discovers all 10 tools from AntChain through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries AntChain, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Block Exploration — Query detailed information about any block by height or hash, including transaction counts and timestamps
Transaction Tracking — Inspect individual transactions by hash or ID, verifying status, gas consumption, and execution results
Smart Contract Management — Deploy new contracts, invoke contract methods, and query contract metadata and ABIs
Account Inspection — Check account balances, nonce values, and metadata for any wallet address on the chain
Network Monitoring — View network topology, node status, consensus state, and chain health metrics
Chain Discovery — List all blockchain networks available to your organization with their configurations
Recent Activity — Monitor the latest transactions and network activity in real-time

The AntChain MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect AntChain to OpenAI Agents SDK via MCP

Follow these steps to integrate the AntChain MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from AntChain

Why Use OpenAI Agents SDK with the AntChain MCP Server

OpenAI Agents SDK provides unique advantages when paired with AntChain through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

AntChain + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the AntChain MCP Server delivers measurable value.

Automated workflows: build agents that query AntChain, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries AntChain, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through AntChain tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query AntChain to resolve tickets, look up records, and update statuses without human intervention

AntChain MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect AntChain to OpenAI Agents SDK via MCP:

deploy_contract

Requires the contract bytecode (compiled bytecode in hex format) and optionally the ABI (Application Binary Interface) for interaction. Returns the deployed contract address and deployment transaction details. The contract will be available under the specified name. Deploy a smart contract on AntChain

get_chain_list

Returns chain IDs, names, creation dates, status, and basic configuration. Use this to discover which blockchains you have access to before performing operations. List all available blockchain networks in your AntChain account

invoke_contract

Provide the contract name, method name, and any required arguments. Returns the execution result including return values, gas consumption, and transaction status. Use this to interact with deployed contracts. Invoke a smart contract method on AntChain

query_account

Use this to inspect account state and activity. Query account information on AntChain

query_account_balance

Returns the available balance and any locked/pending amounts. Useful for checking if an account has sufficient funds for transactions or contract interactions. Query account balance on AntChain

query_block

Returns block metadata including timestamp, transaction count, hash, and previous block reference. Use either blockHeight or blockHash to identify the block. Query block details from an AntChain blockchain

query_contract

Useful for inspecting contract configuration before invocation. Query smart contract information on AntChain

query_latest_transactions

Useful for monitoring network activity, auditing recent transactions, or getting a snapshot of current blockchain operations. Returns a list of recent transactions with their status and metadata. Query the latest transactions on an AntChain blockchain

query_network_info

Useful for monitoring blockchain infrastructure health. Query blockchain network information on AntChain

query_transaction

Returns transaction status, sender, receiver, gas used, block inclusion, and execution result. Useful for verifying transaction finality and inspecting transaction details. Query a transaction on AntChain

Example Prompts for AntChain in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with AntChain immediately.

"Show me the latest 5 transactions on my default AntChain network."

"What's the balance of account 0x742d35Cc6634C0532925a3b844Bc9e7595e0bFa8?"

"Invoke the 'transfer' method on contract 'TokenContract' with args {"to": "0x123...", "amount": 100}."

Troubleshooting AntChain MCP Server with OpenAI Agents SDK

Common issues when connecting AntChain to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

AntChain + OpenAI Agents SDK FAQ

Common questions about integrating AntChain MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.