How to Use the Covalent MCP in Mastra AI

Q: How do I load Covalent tools into a Mastra AI agent?

Install @mastra/mcp and instantiate the client using your Vinkius endpoint. Then, call mcpClient.listTools() and spread the resulting tools directly into your Mastra AI agent configuration.

Q: How do I pause execution for human verification?

Use the requireToolApproval setting in Mastra AI when calling tools like gettokentransfers. This halts the agent's workflow until an admin approves the analyzed transaction data.

Build resilient TypeScript workflows that execute multi-chain Covalent queries and handle failures automatically with Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Covalent MCP to Mastra AI

Create your Vinkius account to connect Covalent 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 Covalent with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Wallet Audits with Mastra Workflows

The `get_historical_portfolio` tool allows your Mastra AI agents to fetch daily balances and historical USD valuations for any active wallet address. You can build a multi-step workflow that analyzes asset drops and automatically triggers notifications if a high-value wallet falls below a specific threshold. If the Covalent API rate limit is reached during heavy audits, Mastra AI handles retries automatically using exponential backoff. You don't have to write custom error-handling loops to keep your portfolio analysis running smoothly.

Human-in-the-Loop Token Transfers

The `get_token_transfers` tool retrieves historical sender and receiver addresses along with transaction timestamps directly into your Mastra AI agent. When analyzing suspicious transfers, you can use the `requireToolApproval` option to pause the agent and ask for human confirmation before flagging a wallet. This setup lets you build compliance workflows that combine automated block scanning with manual overrides. The Mastra AI workflow engine ensures your transaction monitoring agent never executes critical chain actions without explicit permission.

Multi-Chain Status Monitoring MCP Server

The `get_chains_status` tool resolves block height lag, current sync status, and API availability across all networks supported by Covalent. Your Mastra AI agent uses this information to determine which chain is healthy before initiating deeper queries. By integrating this MCP Server, your workflow can dynamically branch based on network health. If a chain is lagging, Mastra AI routes the task to a backup network or alerts your team without crashing your entire system.

Setup guide

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

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

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

Install `@mastra/mcp` and instantiate the client using your Vinkius endpoint. Then, call `mcpClient.listTools()` and spread the resulting tools directly into your Mastra AI agent configuration.

Yes. Mastra AI features a built-in workflow engine that automatically retries failed `get_historical_portfolio` calls using exponential backoff if you hit rate limits.

Yes. You can register the Covalent MCP server within your workflow steps, allowing conditional branching based on the sync status returned by `get_chains_status`.

Use the `requireToolApproval` setting in Mastra AI when calling tools like `get_token_transfers`. This halts the agent's workflow until an admin approves the analyzed transaction data.

The server never stores transaction hashes or wallet addresses passed to `get_transaction_details`. All queries run ephemerally inside the secure Vinkius V8 sandbox, leaving no persistent footprint of your on-chain research.

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