How to Use the Helpjuice MCP in OpenAI Agents SDK

Q: Can I build an agent with the OpenAI Agents SDK to find gaps in my Helpjuice knowledge base?

Yes. A good pattern is to have the agent regularly call getsearchtrends to see what users are searching for, then use searchkb to see if a good answer exists. If not, it can flag the missing topic or even draft an article.

Q: What's the setup process for using Helpjuice with the OpenAI Agents SDK?

You'll instantiate MCPServerStreamableHttp with your Vinkius server URL and token. Then you pass that server object into the mcpservers list when you create your Agent. The agent handles tool discovery automatically.

Build production-ready support agents for Helpjuice with the OpenAI Agents SDK. Manage your KB with full tracing and safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Helpjuice MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate KB Curation Safely

Give your agent the tools to manage your knowledge base. It can use `get_article_stats` and `get_search_trends` to identify stale or missing content, then draft changes with `create_article` or `update_article`. The OpenAI Agents SDK provides guardrails, giving you the chance to review and approve any content changes before they go live. This prevents an autonomous agent from accidentally deleting critical articles or publishing incorrect information. You get automation without the risk.

Build Multi-Agent Support Systems

Go beyond single-purpose bots. The SDK's agent handoff feature lets you build a team of specialized agents. For example, a 'Researcher' agent can monitor user searches with `get_search_trends` to spot a new issue, then pass the context to a 'Writer' agent to draft a new article using `create_article`. This division of labor is perfect for complex support workflows. One agent can `search_kb` to find existing answers while another uses `list_kb_users` to assign a human expert for review. Every action is tracked in the OpenAI dashboard.

Instant Tool Discovery with this MCP Server

There's no manual schema definition required. Just connect the Helpjuice MCP Server to the `MCPServerStreamableHttp` client, and your agent automatically discovers all 12 tools, from `list_articles` to `upvote_article`. Set `cacheToolsList=True` in the constructor for better performance in production. Your agent is immediately ready to analyze KB health with `get_article_stats` or see what your users are looking for with `get_search_trends`. It just works.

Setup guide

Set up Helpjuice 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 Helpjuice tools at runtime.
3

Create your Agent

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

Run the agent

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

The SDK has built-in guardrails that can require human approval before executing sensitive actions. You can let an agent draft an update with `update_article`, but force a manual review before the change is actually saved in Helpjuice.

Yes. A good pattern is to have the agent regularly call `get_search_trends` to see what users are searching for, then use `search_kb` to see if a good answer exists. If not, it can flag the missing topic or even draft an article.

You'll instantiate `MCPServerStreamableHttp` with your Vinkius server URL and token. Then you pass that server object into the `mcp_servers` list when you create your `Agent`. The agent handles tool discovery automatically.

The MCP server exposes all available tools by default. You would enforce tool restrictions within your agent's own logic or prompt, instructing it which tools it is or is not allowed to use for a given task.

Vinkius processes your Helpjuice article content, titles, and analytics data inside an ephemeral sandbox for each request. Your API key for this MCP server is encrypted at rest and is only used to proxy authenticated requests to your Helpjuice instance.

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