How to Use the Exa MCP in Mastra AI

Q: Does Mastra AI support tool approval for Exa?

Yes. You can enable requireToolApproval to verify any search or content extraction before the agent proceeds.

Build resilient web research workflows in Mastra AI. Handle failures and retries automatically with this 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 Exa MCP to Mastra AI

Create your Vinkius account to connect Exa 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 Exa with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate complex research flows

Chain `search` and `find_similar` within your Mastra agents to build deep research loops. If a call fails, the framework handles the retry logic for you. This setup allows you to build multi-step workflows that actually finish. You define the logic, and the tools perform the heavy lifting.

Reliable content retrieval

Use `search_with_contents` to grab data and feed it into your next agent task. The output is structured and ready for immediate processing by your workflow engine. It eliminates the need for manual parsing scripts. Your agents receive clean, usable content every single time.

Conditional search branching

Implement logic that switches between `search_neural` and `search_keyword` based on query complexity. Your workflow adapts to the task at hand. This ensures you aren't wasting compute on expensive semantic lookups for simple entity matches. You keep your API costs predictable.

Setup guide

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

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

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

Absolutely. Just add the server to your agent configuration and use the tools within your step definitions.

Yes. You can enable `requireToolApproval` to verify any search or content extraction before the agent proceeds.

Use the framework's built-in retry mechanisms. If a search fails, the agent will attempt the operation again based on your defined policy.

You can. Chain any of the 10 tools together to build a complete research agent that acts autonomously.

The server only processes the specific web content you request during a workflow run. It does not store or persist your research activity.

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

Mastra AI sdk-typescript

Start using the Exa MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started