How to Use the Conduit MCP in Mastra AI

Q: How do I register Conduit tools inside a Mastra AI agent?

Install @mastra/mcp@latest and initialize the client using your Vinkius HTTP endpoint. Pull the tools using mcpClient.listTools() and spread them directly into your agent's tool configuration array.

Q: Can Mastra AI automatically retry a failed Conduit workflow run?

Yes. Your Mastra agent monitors runs using getrunstatus. If it detects a failure, you can configure Mastra's built-in workflow engine to automatically invoke triggerworkflow up to your specified retry limit.

Q: How does Mastra AI handle Conduit tool approval?

You can wrap the triggerworkflow tool in Mastra's requireToolApproval hook. This forces the agent to get explicit confirmation from a developer before initiating any data migration pipelines.

Build self-healing TypeScript data pipelines using Mastra AI workflows and Conduit monitoring tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Conduit MCP to Mastra AI

Create your Vinkius account to connect Conduit 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 Conduit with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Self-Healing Conduit Workflows with Mastra AI

The `get_run_status` tool provides the exact error messages and execution times your Mastra AI workflow needs to handle pipeline failures. When a run fails, the framework catches the error and executes your custom retry logic with exponential backoff. By combining `list_workflow_runs` with Mastra's conditional branching, your agent detects stuck pipelines and triggers remediations. The agent automatically runs alternative steps if a primary data source goes offline.

Dynamic Source and Destination Routing

The `list_connections` tool allows your Mastra agent to inspect your active data topography before executing sync jobs. By connecting this MCP Server, your agent queries active pipelines to prevent data loss. Your TypeScript agent uses this live connection data to reconfigure flows on the fly. This prevents data loss by halting triggers when the destination connector reports a critical error state.

Approved Triggers via Mastra MCP Server Integration

The `trigger_workflow` tool initiates pipeline runs, but you can restrict this action using Mastra's human-in-the-loop approval gates. When the agent decides to trigger a sync, the framework pauses execution and prompts an admin for confirmation. Once approved, the agent calls `get_workflow` to check the pipeline configuration before starting the run. That's how you keep your production environments safe while keeping the rest of your monitoring automated.

Setup guide

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

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

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

Install `@mastra/mcp@latest` and initialize the client using your Vinkius HTTP endpoint. Pull the tools using `mcpClient.listTools()` and spread them directly into your agent's tool configuration array.

Yes. Your Mastra agent monitors runs using `get_run_status`. If it detects a failure, you can configure Mastra's built-in workflow engine to automatically invoke `trigger_workflow` up to your specified retry limit.

You can wrap the `trigger_workflow` tool in Mastra's `requireToolApproval` hook. This forces the agent to get explicit confirmation from a developer before initiating any data migration pipelines.

Yes. The Mastra client auto-detects SSE and Streamable HTTP transports exposed by Vinkius, ensuring reliable communication with the server without manual transport configuration.

Your database credentials, source URLs, and run history remain isolated. Vinkius runs this MCP Server in zero-trust sandboxes, so your data integration definitions are never exposed to external telemetry platforms.

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