How to Use the Cloze MCP in OpenAI Agents SDK

Q: How do I add the Cloze MCP Server to my OpenAI Agents SDK setup?

Install the SDK, then initialize the server using MCPServerStreamableHttp with your Vinkius endpoint to expose Cloze tools. Pass this server instance inside the mcpservers list when creating your OpenAI Agents SDK constructor.

Q: How do I optimize tool discovery latency for Cloze tools?

Set cacheToolsList=True in your server parameters to prevent the OpenAI Agents SDK from querying the Cloze schema on every turn. This keeps your agent responses fast when they search for contacts using searchpeoplebytag.

Build production-ready OpenAI Agents SDK systems that manage your Cloze contacts and deals with built-in execution guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cloze MCP to OpenAI Agents SDK

Create your Vinkius account to connect Cloze 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 Cloze with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe Contact Updates with OpenAI Agents SDK

When your OpenAI Agents SDK pipeline needs to modify Cloze contact emails, you can't risk corrupted records. This MCP Server lets your agents call `update_person` or `create_person` while the SDK's built-in guardrails validate every single parameter before writing to Cloze. If an agent tries to write bad contact data to Cloze, the OpenAI Agents SDK catches the error and stops the execution. You get clean CRM updates and full execution tracing right in your OpenAI dashboard.

Autonomous Deal Pipeline Management

Let your OpenAI Agents SDK system monitor Cloze projects and properties without manual intervention. By exposing `list_projects` and `create_project` to your agent system, you can build specialized agents that hand off tasks to each other as deals progress. One agent can pull the current Cloze deal list, identify stalled properties, and hand the context over to a communications agent. This keeps your pipeline moving in Cloze without you writing custom routing logic in Python.

Target Prospects Using Tag Searches

Your OpenAI Agents SDK system can instantly segment your network by calling `search_people_by_tag` and `list_companies` through the MCP interface. The SDK auto-discovers these tools, allowing your custom agents to find the right Cloze contacts based on active campaign tags. Once found, the agent uses `get_person` to pull full historical interactions from Cloze. It does all of this within your secure runtime, so your raw CRM data never leaks out of the agent's context window.

Setup guide

Set up Cloze 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 Cloze tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Cloze 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="Cloze Agent",
            instructions="You have access to Cloze 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 Cloze. 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 Cloze 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 Cloze MCP in OpenAI Agents SDK

Install the SDK, then initialize the server using `MCPServerStreamableHttp` with your Vinkius endpoint to expose Cloze tools. Pass this server instance inside the `mcp_servers` list when creating your OpenAI Agents SDK constructor.

Yes, the OpenAI Agents SDK handles concurrent execution out of the box when your agents need to run multiple Cloze tools. If an agent needs to call `list_people` and `list_companies` at the same time, the SDK manages the async requests to Cloze efficiently.

Yes, the framework reads the MCP schema to discover custom CRM fields from Cloze. Your agents can call `list_custom_fields` to inspect how your CRM is structured before calling `create_person`.

Set `cacheToolsList=True` in your server parameters to prevent the OpenAI Agents SDK from querying the Cloze schema on every turn. This keeps your agent responses fast when they search for contacts using `search_people_by_tag`.

Your customer contacts, emails, and deal histories are protected because the Vinkius sandbox acts as a zero-trust intermediary. The OpenAI Agents SDK communicates over secure HTTPS, meaning your actual Cloze credentials never touch the LLM provider directly.

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