How to Use the Dialog Insight MCP in OpenAI Agents SDK

Q: How do I register the Dialog Insight MCP Server in my OpenAI Agents SDK setup?

You initialize MCPServerStreamableHttp with your Vinkius endpoint URL. Pass this instance in the mcpservers list when creating your Agent, and set cacheToolsList=True to speed up tool discovery.

Q: Can my OpenAI Agents SDK search for contacts in Dialog Insight?

Yes, your agent uses searchcontactsbyemail to query the database. It then feeds the result into getcontactprofile to build a complete picture of the user's interaction history.

Q: Does this Dialog Insight integration support OpenAI Agents SDK multi-agent handoffs?

Yes. You can have one agent use listmarketingcontacts to find inactive users, then hand off to a specialized marketing agent that calls listaudiencesegments over the MCP connection.

Q: How do I check my API limits within the agent loop?

Your agent calls getaccountmetadata to read current rate limits and settings. You can write a guardrail that pauses agent execution if the remaining API quota drops below 10%.

Connect your OpenAI Agents SDK to Dialog Insight to automate contact management and track campaign performance safely.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dialog Insight MCP to OpenAI Agents SDK

Create your Vinkius account to connect Dialog Insight 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 Dialog Insight with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run safe contact updates with OpenAI Agents SDK

The `add_new_marketing_contact` tool writes new records directly to your Dialog Insight database. Your agent auto-discovers this capability during initialization, allowing it to instantly route incoming leads to your main lists without manual API mapping. Because the OpenAI Agents SDK enforces strict verification, you can intercept the tool call before execution. If your agent tries to use `search_contacts_by_email` to find a profile, you can inspect the arguments to ensure they comply with your internal compliance rules before passing them to the live endpoint.

Track campaign metrics with built-in guardrails

The `get_campaign_performance` tool pulls raw engagement data directly into your agent's reasoning loop. You configure the MCP server as an HTTP stream, giving your specialized agents access to click rates, open rates, and bounces on demand. Using the OpenAI dashboard, you can view logs for every single execution of `list_high_performing_campaigns`. This gives you full tracing on how your agent parses these performance lists, making it easy to debug the exact logic behind automated list adjustments.

Manage active automations using the MCP Server

The `list_active_automations` tool exposes your current marketing workflows to your OpenAI agent. This allows the system to determine which automated sequences are running before it modifies any customer records. By combining this tool with `list_audience_segments`, your agent can check if a contact belongs to an active campaign before adding them to a new list. This prevents duplicate messaging and keeps your customer communication clean.

Setup guide

Set up Dialog Insight 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 Dialog Insight tools at runtime.
3

Create your Agent

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

Run the agent

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

You initialize `MCPServerStreamableHttp` with your Vinkius endpoint URL. Pass this instance in the `mcp_servers` list when creating your Agent, and set `cacheToolsList=True` to speed up tool discovery.

Yes, your agent uses `search_contacts_by_email` to query the database. It then feeds the result into `get_contact_profile` to build a complete picture of the user's interaction history.

Yes. You can have one agent use `list_marketing_contacts` to find inactive users, then hand off to a specialized marketing agent that calls `list_audience_segments` over the MCP connection.

Your agent calls `get_account_metadata` to read current rate limits and settings. You can write a guardrail that pauses agent execution if the remaining API quota drops below 10%.

Vinkius runs the server in an isolated V8 sandbox that destroys itself after execution. Your API keys are encrypted at rest, and your raw contact data never leaves the secure memory space of the sandbox.

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