How to Use the Doofinder MCP in Mastra AI

Q: Can a Mastra AI agent automatically fix a broken Doofinder index?

The agent uses getindices to identify active arrays and detect configuration mismatches. While it cannot rebuild the index directly, it triggers workflow branches to alert your catalog team.

Q: How does Mastra AI handle rate limits when querying Doofinder stats?

Mastra AI uses its built-in workflow engine to execute getstats with automatic retries and exponential backoff. This prevents your workflows from failing if you hit temporary API limits.

Q: Can I run custom Doofinder search queries inside a Mastra AI workflow?

Yes, you run searchcustom to execute raw, structured queries against your search index. The agent processes the returned payload to make routing decisions or trigger downstream inventory actions.

Q: How do we register these MCP search tools inside our agent code?

Instantiate the client using new MCPClient, call listTools(), and spread the returned tools directly into your agent's tool configuration array.

Run automated e-commerce workflows by connecting Doofinder to Mastra AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Doofinder MCP to Mastra AI

Create your Vinkius account to connect Doofinder 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 Doofinder with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track Doofinder search engine health with Mastra AI agents

The `get_search_engines` tool pulls your current Doofinder configurations to verify your search endpoints are active via this Mastra AI workflow. Your Mastra AI workflows run this check on a schedule, alerting your team if a Doofinder search endpoint goes offline. If the Doofinder check fails, the Mastra AI workflow engine triggers automated retries with exponential backoff. This ensures transient network hiccups between Mastra AI and Doofinder don't trigger false alarms.

Audit Doofinder index discrepancies using this MCP Server

The `get_items` tool inspects your deep internal product arrays to detect indexing anomalies or missing SKUs in your Doofinder catalog. Mastra AI agents run this tool to compare your live database records with what is actually searchable on your storefront. When the Mastra AI agent detects a missing product, it branches the workflow to log the discrepancy. You get automated reports pointing out exactly which SKUs failed to index in Doofinder without manual database lookups.

Compile Doofinder conversion insights directly into workflows

The `get_stats` tool extracts search analytics and click-through rates directly from your active Doofinder search engines. Mastra AI uses this MCP tool to feed historical search performance data into your automated weekly marketing workflows. The Mastra AI agent reads these metrics, flags search queries that returned zero results, and drafts suggested synonyms. This loop runs entirely in the background, keeping your search relevance optimized without human intervention.

Setup guide

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

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

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

The agent uses `get_indices` to identify active arrays and detect configuration mismatches. While it cannot rebuild the index directly, it triggers workflow branches to alert your catalog team.

Mastra AI uses its built-in workflow engine to execute `get_stats` with automatic retries and exponential backoff. This prevents your workflows from failing if you hit temporary API limits.

Yes, you run `search_custom` to execute raw, structured queries against your search index. The agent processes the returned payload to make routing decisions or trigger downstream inventory actions.

Instantiate the client using `new MCPClient`, call `listTools()`, and spread the returned tools directly into your agent's tool configuration array.

All credentials run in memory within your local or cloud host, passing through an ephemeral MCP sandbox. No search statistics or catalog structures are stored on Vinkius servers.

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