How to Use the Convex MCP in Mastra AI

Build complex, multi-step workflows in Mastra AI using direct access to your Convex backend functions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Convex MCP to Mastra AI

Create your Vinkius account to connect Convex 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 Convex with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Convex calls in Mastra AI agents

Use `run_query` and `run_mutation` to build logic trees that react to database changes. You define the flow and the agent handles the execution sequence. This works perfectly for background jobs that require database verification. No more writing custom glue code for every step.

Handle backend logic with Mastra AI and Convex

Call `run_action` to initiate server-side tasks from within your agent workflow. It handles the request lifecycle as part of your established pipeline. You get clear visibility into every step of the process. Debugging becomes simple when you track the agent's calls through your logs.

Manage state transitions for Mastra AI and Convex

Use the server to keep your application state synced across different agent steps. Every `run_function` call ensures your backend reflects the agent's current progress. This creates a reliable record of what your agents actually did. You can review the history to see exactly how your data changed.

Setup guide

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

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

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

Add the server URL to your Mastra client configuration and list the tools. Once initialized, your agents can call your functions as part of their standard toolset.

You can configure your Mastra workflows to catch errors from the server. If a call fails, the framework triggers your retry logic automatically.

Access is restricted to the specific endpoints you define in your backend. The connection uses a unique token, ensuring that only authorized agents can read or write your records.

Yes, you can enable approval requirements for any tool call. This forces the agent to pause until you verify the action in your dashboard.

Check the execution logs in your dashboard to see timing data for each call. It shows you exactly how long your backend functions take to respond.

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