Can it delete documents from my search engines?

Yes. The `st.delete_documents` tool removes specific documents by ID from an engine. Each deletion requires explicit document IDs, so nothing is removed accidentally.

Does it support search analytics like CTR?

Yes. Use `st.analytics_top_searches` and `st.analytics_top_clicks` to retrieve real usage data — top queries, click-through rates, and conversion metrics.

What Swiftype plan is required?

Any plan that includes Site Search API access. You need a valid API key from your Swiftype dashboard — the integration uses standard REST endpoints available to all API-enabled accounts.

Swiftype MCP Server for Mastra AI 10 tools — connect in under 2 minutes

Name: Swiftype
Availability: InStock
Author: Vinkius

docs.mastra.ai/docs/agents/mcp-tools

Built by Vinkius GDPR 10 Tools SDK

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

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

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: {
      "swiftype": {
        url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
      },
    },
  });

  const tools = await mcpClient.getTools();
  const agent = new Agent({
    name: "Swiftype Agent",
    instructions:
      "You help users interact with Swiftype " +
      "using 10 tools.",
    model: openai("gpt-4o"),
    tools,
  });

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

main();

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 Swiftype MCP Server

Empower your conversational AI with robust enterprise search capabilities by securely integrating the Swiftype (Elastic) MCP connector. Stop navigating web dashbaords to manage indexing logic; allow your LLM to act as a direct data architect interacting with your core Swiftype endpoints natively. With full support for reading, creating, and deleting JSON documents on the fly, inspecting live search engine queries, and querying direct analytical metrics like top clicks—this connector brings headless search administration straight to your preferred prompt environment.

Mastra's agent abstraction provides a clean separation between LLM logic and Swiftype tool infrastructure. Connect 10 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

Headless Search & Suggestions — Execute strict queries interrogating custom content engines running st.post_search and provide predictive autocompletes processing st.post_suggest.
CRUD Document Indexing — Pull exact active records from isolated data maps using st.list_documents, inject new payload structures in bulk operating st.create_documents, or vaporize explicit keys commanding st.delete_documents.
Architectural Discovery — Browse registered core scopes applying st.list_engines and parse schema blueprints identifying object hierarchies with st.list_doc_types.
Search Analytics & CTR — Uncover real-world operational user conversion intent evaluating actual volume via st.analytics_top_searches and calculating active hit paths invoking st.analytics_top_clicks.

The Swiftype MCP Server exposes 10 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 Swiftype to Mastra AI via MCP

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

Install dependencies

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

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

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

Explore tools

Mastra discovers 10 tools from Swiftype via MCP

Why Use Mastra AI with the Swiftype MCP Server

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

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

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

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

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

Swiftype + Mastra AI Use Cases

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

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

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

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

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

Swiftype MCP Tools for Mastra AI (10)

These 10 tools become available when you connect Swiftype to Mastra AI via MCP:

st.analytics_top_clicks

Identify precise active arrays spanning native Hold parsing

st.analytics_top_searches

Inspect deep internal arrays mitigating specific Plan Math

st.create_documents

Enumerate explicitly attached structured rules exporting active Billing

st.delete_documents

json` eliminating cached pages permanently erasing bounds metrics from search. Dispatch an automated validation check routing explicit Gateway history

st.list_doc_types

json` extracting schema blueprints enforcing exact map types correctly. Retrieve explicit Cloud logging tracing explicit Vault limits

st.list_documents

json` dumping all stored metadata physically tracking IDs per document type. Irreversibly vaporize explicit validations extracting rich Churn flags

st.list_domains

json` verifying automated crawler limits mapped inside explicit index scopes. Identify precise active arrays spanning native Gateway auth

st.list_engines

json` extracting all active isolated Elastic indices bound per tenant. Identify bounded CRM records inside the Headless Swiftype Platform

st.post_search

json` firing raw queries into the specific Engine returning faceted JSON hierarchies. Perform structural extraction of properties driving active Account logic

st.post_suggest

json` bounding predictive keys and spelling tolerant matches decoupled from main indexing. Provision a highly-available JSON Payload generating hard Customer bindings

Example Prompts for Swiftype in Mastra AI

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

"List all my available Swiftype search engines, then run a search for 'documentation' on the most relevant one and show me the top 3 analytics clicks it generated last week."

"List all active engines in our Swiftype account."

"Run a test suggestion for 'passw' in the internal wiki engine."