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 OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Swiftype
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Swiftype through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

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.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Swiftype Assistant",
            instructions=(
                "You help users interact with Swiftype. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Swiftype"
        )
        print(result.final_output)

asyncio.run(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.

The OpenAI Agents SDK auto-discovers all 10 tools from Swiftype through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Swiftype, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

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 OpenAI Agents SDK 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 OpenAI Agents SDK via MCP

Follow these steps to integrate the Swiftype MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Swiftype

Why Use OpenAI Agents SDK with the Swiftype MCP Server

OpenAI Agents SDK provides unique advantages when paired with Swiftype through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Swiftype + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Swiftype MCP Server delivers measurable value.

Automated workflows: build agents that query Swiftype, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Swiftype, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Swiftype tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Swiftype to resolve tickets, look up records, and update statuses without human intervention

Swiftype MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Swiftype to OpenAI Agents SDK 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 OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK 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."

Troubleshooting Swiftype MCP Server with OpenAI Agents SDK

Common issues when connecting Swiftype to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Swiftype + OpenAI Agents SDK FAQ

Common questions about integrating Swiftype MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.