How to Use the Conflux MCP in LangChain

Q: How do I register the Conflux MCP Server in a LangChain project?

Install the adapter package using pip install langchain-mcp-adapters langgraph. Then, initialize the MultiServerMCPClient with the Vinkius endpoint URL and pass the tools returned by client.gettools() directly into your agent creator.

Q: How does LangChain handle gas estimation failures on Conflux?

Your agent catches errors from cfxestimategasandcollateral or ethestimategas within the tool call step. You can configure your chain to retry with different parameters or alert you if a contract call reverts during local simulation.

Q: Does this setup support tracking real-time events?

Absolutely. You can chain cfxgetlogs with your LangChain agent to poll for specific smart contract events and feed those logs into downstream data processors or notification systems.

Pipe live blockchain data from Conflux directly into your LangChain reasoning chains to automate transaction tracking and contract reads.

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 LangChain

Create your Vinkius account to connect Conflux to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Read Core and eSpace ledger states in LangChain

The Conflux MCP Server exposes direct read tools like `cfx_get_balance` and `eth_get_balance` to feed live token balances straight into your LangChain agent's active memory. Your agent uses these tools to inspect account states on both Core Space and eSpace without you writing custom RPC wrappers. By chaining these inputs, your ReAct agent can automatically check a user's balance before deciding whether to trigger a contract call. Every single transaction query feeds directly into the next link of your chain, backed by LangSmith tracing to watch every step.

Verify contract executions and gas limits

Executing read-only contract calls is handled by `cfx_call` and `eth_call`, giving your agent the ability to inspect smart contracts on the fly. You run local simulations to verify code behavior before putting real capital on the line. If gas estimation is what you need, the server provides `cfx_estimate_gas_and_collateral` and `eth_estimate_gas` to calculate transaction costs. Your LangChain pipelines use these values to dynamically adjust parameters, keeping your automated transactions from failing due to out-of-gas errors.

Track transactions and epoch blocks automatically

Tracking transactions across the dual-space network uses `cfx_get_transaction_receipt` and `eth_get_transaction_receipt` to pull instant execution statuses. Your agent can monitor a pending transaction, wait for confirmation, and inspect the logs using `cfx_get_logs` or `eth_get_logs`. This setup lets you build autonomous monitoring chains using this MCP Server to watch epoch changes via `cfx_get_blocks_by_epoch` and trigger alerts when specific events occur. You get a complete, observable pipeline of blockchain events flowing directly into your application.

Setup guide

Set up Conflux MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Conflux tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "conflux-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Conflux transactions"
    })
    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 LangChain

Install the adapter package using `pip install langchain-mcp-adapters langgraph`. Then, initialize the `MultiServerMCPClient` with the Vinkius endpoint URL and pass the tools returned by `client.get_tools()` directly into your agent creator.

Yes, the server exposes parallel tools for both spaces. Your agent will use the `eth_` prefix tools for EVM-compatible eSpace queries and the `cfx_` prefix tools for Core Space operations.

Your agent catches errors from `cfx_estimate_gas_and_collateral` or `eth_estimate_gas` within the tool call step. You can configure your chain to retry with different parameters or alert you if a contract call reverts during local simulation.

Absolutely. You can chain `cfx_get_logs` with your LangChain agent to poll for specific smart contract events and feed those logs into downstream data processors or notification systems.

This server only handles public blockchain data like addresses, transaction receipts, block hashes, and epoch numbers. Because Vinkius runs this MCP Server in an isolated, zero-trust sandbox, your private keys and sensitive environment variables never leave your local client.

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