How to Use the Conflux MCP in Mastra AI

Q: Does this Conflux MCP Server support human approval?

Yes, you use the requireToolApproval flag in your agent setup. It forces the agent to pause before executing any transaction-sending tool.

Build complex blockchain workflows in Mastra AI with this Conflux MCP Server.

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 Mastra AI

Create your Vinkius account to connect Conflux to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain logic for Mastra AI agents

Chain together contract calls using `cfx_call` or `eth_call`. Your Mastra agents handle the conditional logic when those calls return data. If a query fails, your agent can retry the operation automatically. It turns raw blockchain responses into reliable workflow steps.

Automated Conflux monitoring in Mastra AI

Set up agents to watch for specific logs using `cfx_get_logs` or `eth_get_logs`. You build triggers that react when a transaction hits the chain. This creates a loop where your agent stays informed. It handles the polling so you don't have to write custom cron jobs.

Gas estimation for Mastra AI transactions

Calculate costs before sending anything by calling `cfx_estimate_gas_and_collateral` or `eth_estimate_gas`. Your agent checks these values to ensure the transaction succeeds. It adds a layer of safety to your automated processes. You avoid wasting gas on failed contract execution.

Setup guide

Set up Conflux MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Conflux tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "conflux-mcp-client",
  servers: {
    "conflux-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Conflux Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Conflux tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Conflux transactions"
);
console.log(result.text);

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 Mastra AI

You instantiate the client with the server URL and spread the tools into your agent definition. This gives the agent access to all blockchain query functions.

Mastra handles retries natively. You configure the backoff policy, and the agent re-runs the tool until it succeeds or hits your limit.

Yes, you use the `requireToolApproval` flag in your agent setup. It forces the agent to pause before executing any transaction-sending tool.

The server supports both Core Space and eSpace. You call the specific tools for the network your workflow targets.

The server operates in an ephemeral sandbox. It only processes the transaction payloads you provide and discards them after the request completes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.