How to Use the Dashly MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK connect to Dashly?

You instantiate the MCPServerStreamableHttp class with your Vinkius endpoint URL and pass it to your Agent constructor. The Dashly tools are discovered automatically by the agent through the MCP standard.

Build production-ready support agents for Dashly with the OpenAI Agents SDK. Guardrails and tracing are built right in.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dashly MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Respond to Customers Automatically

This tool connects your OpenAI agent to Dashly, letting it handle common support questions. It can pull context using `get_conversation` and `get_user_details`, then send a response with `send_reply`. This isn't just a toy; it's for building real, automated support flows. Because the SDK has built-in guardrails, you can review and approve actions before they execute. That gives you a safety net for production systems, preventing your agent from sending the wrong message to a real customer.

Engage Users Based on Their Actions

Use your agent to watch for specific user behavior inside your app. The `track_event` tool logs actions in Dashly, and your agent can react by setting custom properties with `set_user_props`. The OpenAI Agents SDK supports handoffs, so you can build sophisticated workflows. One agent could monitor events, then pass control to a specialized agent that takes over to nurture the lead. Full tracing in the OpenAI dashboard shows you exactly what happened.

Query Dashly Data with the MCP Server

Give your agent a simple way to look up information inside Dashly. It can get lists of recent chats with `list_conversations` or find specific people with `list_users`. Your agent discovers these tools automatically. Just point it at this MCP Server endpoint and it's ready to work. There's no manual tool definition or boilerplate code required.

Setup guide

Set up Dashly 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 Dashly tools at runtime.
3

Create your Agent

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

Run the agent

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

You instantiate the `MCPServerStreamableHttp` class with your Vinkius endpoint URL and pass it to your Agent constructor. The Dashly tools are discovered automatically by the agent through the MCP standard.

Your agent can perform eight actions. It can list and get conversations, list and get users, send replies, set user properties, track events, and list communication channels inside Dashly.

Yes. The OpenAI Agents SDK has built-in guardrails that allow for human-in-the-loop validation. You can configure your agent to require approval before executing an action like `send_reply`.

It saves you from writing and maintaining a bunch of API client code. The MCP server provides a standardized interface that your agent understands out of the box, complete with authentication and automatic tool discovery.

Your connection runs in a V8 Isolate sandbox on Vinkius, completely isolated from other tenants. We handle the authentication, and the server instance itself is ephemeral, processing your customer conversation data without storing it long-term.

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