How to Use the Mnemonic MCP in Mastra AI

Q: How do I register the Mnemonic MCP server in Mastra AI?

Instantiate the client using the @mastra/mcp package and point it to your Vinkius endpoint URL. You then register the server in your agent configuration, exposing the tools for autonomous execution. Mastra automatically manages the underlying transport layer.

Q: Can I require manual approval for Mnemonic tools in Mastra AI?

Yes, you can use the requireToolApproval flag on specific tools like listtransfers or getwallethistory. This forces the workflow to halt and wait for human confirmation before retrieving sensitive ledger data. It is a great way to control API consumption.

Build resilient, automated NFT workflows and trading agents with Mastra AI and the Mnemonic 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 Mnemonic MCP to Mastra AI

Create your Vinkius account to connect Mnemonic 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 Mnemonic with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build resilient workflows with Mastra AI

The `get_nft_prices` tool feeds current valuation metrics directly into your automated decision loops. Mastra handles the conditional logic, letting you set up strict rules to trigger actions when floor prices cross specific thresholds. If a network call fails, the built-in retry engine with exponential backoff ensures your agent does not lose track of the market. This protects your automated pipelines from transient API hiccups.

Track ownership shifts automatically

Your agent uses `get_nft_owners` to monitor who holds high-value assets across target contracts. You can map these addresses against known lists to flag institutional accumulation or retail panic. By integrating `get_collection_distribution`, the workflow evaluates the overall health of a project before executing any automated orders. Let's look at the raw state: if a contract is highly concentrated, you probably want to stay away.

Audit transfer histories safely

The `list_transfers` tool pulls historical transaction events to reconstruct the movement of specific tokens over time. Mastra allows you to inject human-in-the-loop approvals before acting on this historical data. It provides absolute control over tool execution inside the MCP environment. If your agent detects suspicious wash trading patterns via `get_wallet_history`, it pauses the workflow. A human operator can then review the flagged wallet before the system executes a sale.

Setup guide

Set up Mnemonic 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 Mnemonic 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: "mnemonic-mcp-client",
  servers: {
    "mnemonic-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Mnemonic 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 Mnemonic. 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 Mnemonic 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 Mnemonic MCP in Mastra AI

Instantiate the client using the `@mastra/mcp` package and point it to your Vinkius endpoint URL. You then register the server in your agent configuration, exposing the tools for autonomous execution. Mastra automatically manages the underlying transport layer.

Yes, you can use the `requireToolApproval` flag on specific tools like `list_transfers` or `get_wallet_history`. This forces the workflow to halt and wait for human confirmation before retrieving sensitive ledger data. It is a great way to control API consumption.

Mastra has a native workflow engine that supports automatic retries with backoff. If an MCP server call returns a rate-limit error, the system pauses and retries the operation behind the scenes. This ensures your automated trading loops do not crash during high-volume events.

Yes, the client automatically detects and negotiates the correct transport protocol. Whether your Vinkius gateway uses Server-Sent Events or standard HTTP, the framework handles the connection details without manual configuration.

Zero-trust architecture ensures your queries are completely isolated. Your wallet addresses and transaction lookups pass through encrypted channels and are never stored on disk. Vinkius executes the code in ephemeral sandboxes, leaving no trace of your proprietary trading strategies.

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