2,500+ MCP servers ready to use
Vinkius

Exa AI MCP Server for Mastra AI 6 tools — connect in under 2 minutes

Built by Vinkius GDPR 6 Tools SDK

Mastra AI is a TypeScript-native agent framework built for modern web stacks. Connect Exa AI through Vinkius and Mastra agents discover all tools automatically. type-safe, streaming-ready, and deployable anywhere Node.js runs.

Vinkius supports streamable HTTP and SSE.

typescript
import { Agent } from "@mastra/core/agent";
import { createMCPClient } from "@mastra/mcp";
import { openai } from "@ai-sdk/openai";

async function main() {
  // Your Vinkius token. get it at cloud.vinkius.com
  const mcpClient = await createMCPClient({
    servers: {
      "exa-ai": {
        url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
      },
    },
  });

  const tools = await mcpClient.getTools();
  const agent = new Agent({
    name: "Exa AI Agent",
    instructions:
      "You help users interact with Exa AI " +
      "using 6 tools.",
    model: openai("gpt-4o"),
    tools,
  });

  const result = await agent.generate(
    "What can I do with Exa AI?"
  );
  console.log(result.text);
}

main();
Exa AI
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Exa AI MCP Server

Empower your AI agent to orchestrate your entire web discovery and semantic search workflow with Exa AI, the search engine built for the future of AI. By connecting Exa to your agent, you transform complex information gathering into a natural conversation. Your agent can instantly search the web using semantic embeddings, audit similar websites through URL matching, and retrieve cleaned page content without you ever touching a browser. Whether you are conducting deep market research or monitoring niche industry trends, your agent acts as a real-time web analyst, ensuring your intelligence is always grounded in contextually relevant data.

Mastra's agent abstraction provides a clean separation between LLM logic and Exa AI tool infrastructure. Connect 6 tools through Vinkius and use Mastra's built-in workflow engine to chain tool calls with conditional logic, retries, and parallel execution. deployable to any Node.js host in one command.

What you can do

  • Semantic Auditing — Query the web using natural language and retrieve results based on meaning rather than just keywords.
  • Similar Discovery — Find websites similar to any provided URL to identify competitors or related sources instantly.
  • Content Oversight — Retrieve cleaned HTML or text content for any search result to maintain a structured view of web data.
  • Usage Intelligence — Monitor your API usage and crawl statistics to maintain strict control over your research budget.
  • Unified Search — Perform search and content retrieval in a single request to optimize agent response times.

The Exa AI MCP Server exposes 6 tools through the Vinkius. Connect it to Mastra AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Exa AI to Mastra AI via MCP

Follow these steps to integrate the Exa AI MCP Server with Mastra AI.

01

Install dependencies

Run npm install @mastra/core @mastra/mcp @ai-sdk/openai

02

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

03

Run the agent

Save to agent.ts and run with npx tsx agent.ts

04

Explore tools

Mastra discovers 6 tools from Exa AI via MCP

Why Use Mastra AI with the Exa AI MCP Server

Mastra AI provides unique advantages when paired with Exa AI through the Model Context Protocol.

01

Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure. add Exa AI without touching business code

02

Built-in workflow engine chains MCP tool calls with conditional logic, retries, and parallel execution for complex automation

03

TypeScript-native: full type inference for every Exa AI tool response with IDE autocomplete and compile-time checks

04

One-command deployment to any Node.js host. Vercel, Railway, Fly.io, or your own infrastructure

Exa AI + Mastra AI Use Cases

Practical scenarios where Mastra AI combined with the Exa AI MCP Server delivers measurable value.

01

Automated workflows: build multi-step agents that query Exa AI, process results, and trigger downstream actions in a typed pipeline

02

SaaS integrations: embed Exa AI as a first-class tool in your product's AI features with Mastra's clean agent API

03

Background jobs: schedule Mastra agents to query Exa AI on a cron and store results in your database automatically

04

Multi-agent systems: create specialist agents that collaborate using Exa AI tools alongside other MCP servers

Exa AI MCP Tools for Mastra AI (6)

These 6 tools become available when you connect Exa AI to Mastra AI via MCP:

01

find_similar

Find websites similar to a given URL

02

get_api_usage

Get current API usage and crawl statistics

03

get_contents

Get cleaned HTML/text content for specific Exa IDs

04

get_search_links

Get just the top links for a search query

05

search_web

Search the web semantically using Exa

06

search_with_contents

Search and retrieve contents in one request

Example Prompts for Exa AI in Mastra AI

Ready-to-use prompts you can give your Mastra AI agent to start working with Exa AI immediately.

01

"Find 5 high-quality research papers about 'Climate Change mitigation' using Exa."

02

"Find sites similar to https://techcrunch.com."

03

"Search for 'future of AI robotics' and give me the full content of the best result."

Troubleshooting Exa AI MCP Server with Mastra AI

Common issues when connecting Exa AI to Mastra AI through the Vinkius, and how to resolve them.

01

createMCPClient not exported

Install: npm install @mastra/mcp

Exa AI + Mastra AI FAQ

Common questions about integrating Exa AI MCP Server with Mastra AI.

01

How does Mastra AI connect to MCP servers?

Create an MCPClient with the server URL and pass it to your agent. Mastra discovers all tools and makes them available with full TypeScript types.
02

Can Mastra agents use tools from multiple servers?

Yes. Pass multiple MCP clients to the agent constructor. Mastra merges all tool schemas and the agent can call any tool from any server.
03

Does Mastra support workflow orchestration?

Yes. Mastra has a built-in workflow engine that lets you chain MCP tool calls with branching logic, error handling, and parallel execution.

Connect Exa AI to Mastra AI

Get your token, paste the configuration, and start using 6 tools in under 2 minutes. No API key management needed.