How to Use the AddSearch MCP in Mastra AI

Q: How do I add the AddSearch MCP Server to a Mastra AI agent?

You register the server using the MCPClient class pointing to your Vinkius HTTP endpoint. Then, call listTools() on the client and spread those tools directly into your Mastra agent configuration. This exposes all search and indexing capabilities to your workflow loops.

Q: Can Mastra AI handle human approval before AddSearch index changes?

Yes, you can set requireToolApproval on tools like deletedocument or indexdocument. This pauses the Mastra workflow and waits for a human to confirm before any pages are wiped or modified in your index.

Q: How do I filter search results dynamically using AddSearch and Mastra AI?

Your agent uses the searchfiltered tool to narrow down results based on custom parameters like categories or tags. Mastra AI passes these structured parameters directly from its step context, allowing you to build highly targeted search pipelines.

Build automated search optimization workflows in Mastra AI using live site analytics and indexing tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AddSearch MCP to Mastra AI

Create your Vinkius account to connect AddSearch 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 AddSearch with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Content Indexing in Mastra AI Workflows

The `index_document` tool lets your Mastra AI agent automatically update your site search index whenever your CMS triggers a webhook. If a sync fails, Mastra's built-in workflow engine retries the call with exponential backoff. You can set up conditional steps to run `delete_document` if a page goes offline. This ensures your search index stays perfectly aligned with your actual live database without manual intervention.

Analyze Search Trends with Mastra AI Agents

The `stats_queries` tool pulls search query data directly into your automated agent loops. Mastra AI can analyze these search terms to find content gaps on your site automatically. If the agent detects high-volume search terms with zero results, it can trigger a Slack alert or draft a new content brief. You turn passive analytics into immediate editorial action.

Verify Click Performance via MCP Server

The `stats_clicks` tool retrieves click-through analytics so your agent can monitor search performance. The workflow engine evaluates this data to see which pages are underperforming. Using these metrics, your agent can automatically adjust custom fields or tags via `index_document` to boost relevance. This creates a self-optimizing search experience that improves itself over time.

Setup guide

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

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

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

You register the server using the `MCPClient` class pointing to your Vinkius HTTP endpoint. Then, call `listTools()` on the client and spread those tools directly into your Mastra agent configuration. This exposes all search and indexing capabilities to your workflow loops.

Yes, you can set `requireToolApproval` on tools like `delete_document` or `index_document`. This pauses the Mastra workflow and waits for a human to confirm before any pages are wiped or modified in your index.

Your agent uses the `search_filtered` tool to narrow down results based on custom parameters like categories or tags. Mastra AI passes these structured parameters directly from its step context, allowing you to build highly targeted search pipelines.

Mastra uses its built-in retry mechanism to handle transient network errors when calling `index_document`. If the failure persists, the workflow branches to your error-handling path, which can notify your team or log the payload for manual review.

Your site documents, search queries, and click metrics are transmitted directly over TLS to the AddSearch API. Vinkius runs your MCP connection inside an isolated V8 sandbox that does not store or log your payload data. This guarantees that your proprietary search analytics and content indices remain completely private.

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