How to Use the AddSearch MCP in OpenAI Agents SDK

Q: How do I connect AddSearch to the OpenAI Agents SDK?

Pass the endpoint URL into MCPServerStreamableHttp. You then hand that object to your Agent constructor using the mcpservers array. Set cacheToolsList=True so your agent discovers the tools faster on startup.

Q: Can OpenAI Agents SDK read my AddSearch autocomplete data?

Yes, the autosuggest tool exposes those exact type-ahead recommendations. Your agent reads these suggestions to predict what users are trying to find before executing a full search.

Q: Does the OpenAI Agents SDK support sorting AddSearch results?

Your agent handles that via the searchsorted tool. It applies custom sort parameters to the query so the highest priority documents always hit the context window first.

Give your OpenAI Agents SDK production-grade access to AddSearch indexes. Push documents and pull analytics with built-in safety constraints.

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 OpenAI Agents SDK

Create your Vinkius account to connect AddSearch to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Management for OpenAI Agents SDK

The `index_document` tool lets your agent push new content directly into your search index. We built this so your data ingestion pipelines can run autonomously while remaining under the strict guardrails of the OpenAI framework. Removing stale data is just as critical. Your system can call `delete_document` to purge outdated records, while you track every single deletion event through your OpenAI dashboard tracing.

Query Analytics and Click Tracking

Stop guessing what users search for. The `stats_queries` tool pulls raw data on search volume and popular terms straight into your agent's context window. You pair that with `stats_clicks` to map out exactly which results drive engagement. Handoff these metrics to a specialized analyst agent to generate weekly performance reports without writing custom API wrappers.

Advanced Search MCP Server Integration

Basic keyword matching rarely cuts it in production. Your agent triggers `search_filtered` to slice through your indexed content using custom fields like brand or category. Large result sets won't overwhelm your token limits. The `search_pagination` tool ensures your agent only loads the specific page of data it actually needs to answer the user's prompt.

Setup guide

Set up AddSearch MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all AddSearch tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives AddSearch tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate AddSearch tools and returns structured results. Copy the full example on the right to get started.

agent.py

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

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="AddSearch Agent",
            instructions="You have access to AddSearch tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Pass the endpoint URL into `MCPServerStreamableHttp`. You then hand that object to your Agent constructor using the `mcp_servers` array. Set `cacheToolsList=True` so your agent discovers the tools faster on startup.

Yes, the `autosuggest` tool exposes those exact type-ahead recommendations. Your agent reads these suggestions to predict what users are trying to find before executing a full search.

Writing custom wrappers means maintaining them forever. This server gives you ten tested tools instantly, and the OpenAI framework handles all the tracing and validation automatically.

Your agent handles that via the `search_sorted` tool. It applies custom sort parameters to the query so the highest priority documents always hit the context window first.

Your indexed site content and search analytics stay within the V8 Isolate Sandbox. Vinkius drops the ephemeral container the second your agent finishes pulling the `stats_clicks` or `list_documents` payload. Nothing persists on our infrastructure.

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