How to Use the Chaindesk MCP in OpenAI Agents SDK

Q: How do I initialize the Chaindesk toolset inside my OpenAI Agents SDK project?

First, install the library and define MCPServerStreamableHttp with your Vinkius URL. Then, pass that instance into your agent's server list.

Q: Can I cache tools to speed up my Chaindesk queries in OpenAI Agents SDK?

Yes, set cacheToolsList to true. This stops the SDK from fetching tool definitions on every turn, saving valuable milliseconds.

Q: Does OpenAI Agents SDK support automatic discovery of Chaindesk tools?

It does. The SDK automatically registers tools like queryagent and listdatastores right out of the box.

Q: What is the best way to handle multi-agent routing for customer support?

Start by building a router agent. That router calls listagents to find the right specialist, then hands off the conversation context.

Run secure, multi-agent customer support workflows by connecting OpenAI Agents SDK to Chaindesk via our managed MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chaindesk MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect Chaindesk MCP Server to OpenAI Agents SDK

This MCP Server lets your OpenAI Agents SDK connect directly to your custom knowledge bases. You don't have to waste time writing custom vector search integrations or database connectors. Your agent triggers `upsert_datasource` to load new files whenever customers upload documents. It then runs `get_datastore` to confirm the ingestion completed before answering.

Control agent behaviors with OpenAI-specific guardrails

This MCP Server provides strict boundaries by validating every tool call before execution. You can block unauthorized administrative commands at the network level. If the model tries executing `delete_agent` during a standard support chat, your middleware halts the process. Your production agents stay safe from rogue inputs.

Track multi-agent handoffs and message history

This MCP Server allows you to coordinate multi-agent support networks by spinning up specialized assistants on demand. You can route complex technical tickets to dedicated nodes. Call `get_messages` to pull historical logs directly into your OpenAI tracing dashboard. This gives you clear visibility into how your agents resolve tickets.

Setup guide

Set up Chaindesk 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 Chaindesk tools at runtime.
3

Create your Agent

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

Run the agent

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

First, install the library and define `MCPServerStreamableHttp` with your Vinkius URL. Then, pass that instance into your agent's server list.

Yes, set `cacheToolsList` to true. This stops the SDK from fetching tool definitions on every turn, saving valuable milliseconds.

It does. The SDK automatically registers tools like `query_agent` and `list_datastores` right out of the box.

Start by building a router agent. That router calls `list_agents` to find the right specialist, then hands off the conversation context.

Vinkius processes all data inside isolated, ephemeral V8 sandboxes. Your text inputs are handled in memory and never stored on disk.

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

Mastra AI sdk-typescript

Start using the Chaindesk MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started