How to Use the VectorShift (AI Workflow & RAG Automation) MCP in OpenAI Agents SDK

Q: What's the fastest way to get information from my documents using VectorShift (AI Workflow & RAG Automation) with the OpenAI Agents SDK?

Querying is fast. You use queryknowledgebase and feed it a semantic search request. This tool searches against your indexed files, giving you context-aware results rather than simple keyword matches.

Q: If I need to update my chatbot's knowledge base using VectorShift (AI Workflow & RAG Automation) with the OpenAI Agents SDK, what tools do I use?

First, you might want to delete old files using deleteknowledgebasedocuments. Then, add new data via indexknowledgebase or upload fresh content directly through the uploadchatbotfiles tool.

Q: Can I stop a running process if it's failing using VectorShift (AI Workflow & RAG Automation) with the OpenAI Agents SDK?

Absolutely. If a pipeline is running too long, use terminatepipeline. Similarly, if a chatbot session goes wild, you can stop it immediately by calling terminatechatbot.

Automate complex AI workflows and RAG pipelines with the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect VectorShift (AI Workflow & RAG Automation) MCP to OpenAI Agents SDK

Create your Vinkius account to connect VectorShift (AI Workflow & RAG Automation) 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 VectorShift (AI Workflow & RAG Automation) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Knowledge Bases

Need to feed your agent external data? You can build a knowledge base, either by calling `create_knowledge_base` or by adding documents directly using `index_knowledge_base`. These tools let you keep track of what information the agent has access to. Once set up, your agent can query that data instantly. The `query_knowledge_base` tool performs semantic search against the indexed content so your AI client gets accurate answers, not just keyword matches.

Build and Run Chatbots

Want an interactive chat experience? Use `create_chatbot` to set up a new session. You can also upload files specific to that chatbot using `upload_chatbot_files`. This gives your agent context beyond its core training data. After setup, calling `run_chatbot` sends a message and gets a response back immediately. If the chat needs to stop, you use `terminate_chatbot`.

Orchestrate Multi-Step Pipelines

A simple task often requires several steps. You can design complex sequences by creating pipelines with `create_pipeline`. These pipelines let you execute multiple actions in a specific order, like processing data and then querying it. The system lets you manage these flows entirely. Use `run_pipeline` to start the whole process, or if things go sideways, use `pause_pipeline` and later resume it with `resume_pipeline`.

Setup guide

Set up VectorShift (AI Workflow & RAG Automation) 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 VectorShift (AI Workflow & RAG Automation) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives VectorShift (AI Workflow & RAG Automation) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate VectorShift (AI Workflow & RAG Automation) 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="VectorShift (AI Workflow & RAG Automation) Agent",
            instructions="You have access to VectorShift (AI Workflow & RAG Automation) 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 VectorShift. 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 VectorShift (AI Workflow & RAG Automation) 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 VectorShift (AI Workflow & RAG Automation) MCP in OpenAI Agents SDK

You execute workflows by running a pipeline instance. Start by calling `run_pipeline` with the necessary inputs. If you need to perform a specific data transformation mid-flow, use `run_transformation`, which executes code written in Python or JavaScript.

Querying is fast. You use `query_knowledge_base` and feed it a semantic search request. This tool searches against your indexed files, giving you context-aware results rather than simple keyword matches.

First, you might want to delete old files using `delete_knowledge_base_documents`. Then, add new data via `index_knowledge_base` or upload fresh content directly through the `upload_chatbot_files` tool.

Absolutely. If a pipeline is running too long, use `terminate_pipeline`. Similarly, if a chatbot session goes wild, you can stop it immediately by calling `terminate_chatbot`.

This MCP Server handles structured text and file content when processing knowledge bases. When you index files or documents, that raw textual data is processed by the server.

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