How to Use the Exa AI MCP in Mastra AI

Q: How do I register the Exa AI MCP Server tools inside Mastra AI?

Instantiate MCPClient from @mastra/mcp with your Vinkius endpoint URL. You can then call listTools() and spread them directly into your Mastra Agent's tool configuration array.

Q: How do Mastra AI retries work when Exa AI returns a rate limit?

Mastra's workflow engine intercepts errors from tools like advancedcustomsearch. You can configure a retry policy that automatically backs off and retries the query, ensuring your automated agents don't crash.

Q: Can I filter search results by category dynamically?

Yes, your agent can call searchbycategory to target specific types of sites, like company blogs or research papers, ensuring the workflow only processes highly relevant document types.

Build resilient, self-healing search workflows with Mastra AI and the Exa AI 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 AI MCP to Mastra AI

Create your Vinkius account to connect Exa AI 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 AI with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step search workflows in Mastra AI

Mastra AI excels at running complex, multi-step agentic pipelines where one step's output dictates the next. You can configure an agent to run `semantic_search` and, if the results lack specific keywords, automatically branch to a `keyword_search` to fill the gaps. By registering this MCP Server with your Mastra instance, your workflow can chain these tools together without writing custom API integration code. The agent handles the data flow from search to decision-making autonomously.

Resilient web crawls with automatic retries

Web extraction is notoriously flaky, but Mastra's built-in workflow engine solves this by handling transient failures gracefully. If a `perform_live_crawl` call hits a rate limit or a target site timeout, Mastra automatically retries with exponential backoff. You can also set up a fallback path that triggers `search_by_crawl_date` to find cached alternatives if a live crawl fails. This ensures your automated background workers never get stuck on a broken external website.

Human-in-the-loop validation for search actions

Sometimes you don't want your Mastra agent pulling raw text from the web without a quick safety check. You can enforce a manual approval step before the agent calls `extract_page_content` on untrusted domains. The agent pauses, alerts your admin, and only resumes the workflow to run `search_with_contents` once a human approves the target URL. This gives you tight control over what external data enters your vector database.

Setup guide

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

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

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

Instantiate `MCPClient` from `@mastra/mcp` with your Vinkius endpoint URL. You can then call `listTools()` and spread them directly into your Mastra Agent's tool configuration array.

Yes, you can write Mastra workflows that inspect the results of `semantic_search` and conditionally trigger `find_similar_pages` or `extract_page_content` depending on the relevance scores returned by the neural engine.

Mastra's workflow engine intercepts errors from tools like `advanced_custom_search`. You can configure a retry policy that automatically backs off and retries the query, ensuring your automated agents don't crash.

Yes, your agent can call `search_by_category` to target specific types of sites, like company blogs or research papers, ensuring the workflow only processes highly relevant document types.

All search parameters, domain filters, and scraped text pass through Vinkius's zero-trust V8 isolate sandbox. This MCP configuration guarantees that your raw search queries and extracted page contents are processed ephemerally and never stored on disk.

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