How to Use the Verba MCP in OpenAI Agents SDK

Q: Does Verba support complex queries with OpenAI Agents SDK?

Yep. You run semantic searches using performragquery. This tool returns summarized answers and provides citations, so you always know where the agent got its facts.

Q: What is the process for deleting data in Verba with OpenAI Agents SDK?

You call deleteknowledgedocument when a document must be permanently removed. Remember, this action is irreversible; always confirm you want to delete it.

Access corporate knowledge for your production agents using 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 Verba MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run RAG queries against Verba MCP Server.

Need answers from your company docs? Use `perform_rag_query` to run a Retrieval Augmented Generation query against the knowledge base. It returns summarized answers and cites exactly where it found that info. It's built for production agents, so you get reliable context every time. You can connect Verba RAG directly to your AI agent flow, managing your Weaviate data store without leaving your system.

Manage core knowledge documents.

Keep the source material clean with these tools. You'll use `add_knowledge_document` when you upload a new document and its metadata JSON. Conversely, if something is obsolete, `delete_knowledge_document` permanently removes it—just be careful, that action is irreversible. You can always check what you have indexed using `list_knowledge_documents`, so your agent never tries to read from an empty pool.

Check system status and details.

Debugging or auditing? You use `get_document_details` to retrieve the full content and metadata for a specific file. If you need to know what rules your agent is following, call `get_system_config`. It pulls the current Verba system configuration. These tools give visibility into the MCP Server's state, which is critical when building production systems that can't afford hidden failures.

Setup guide

Set up Verba 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 Verba tools at runtime.
3

Create your Agent

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

Run the agent

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

You pass the MCP Server object directly to the Agent constructor. This lets your agent auto-discover all available tools, like `perform_rag_query`, so you don't need manual configuration.

You can update the knowledge base by adding new documents via `add_knowledge_document`. The system ingests the content, and your agent instantly has access to the fresh information for better responses.

Yep. You run semantic searches using `perform_rag_query`. This tool returns summarized answers *and* provides citations, so you always know where the agent got its facts.

You call `delete_knowledge_document` when a document must be permanently removed. Remember, this action is irreversible; always confirm you want to delete it.

This server manages structured knowledge documents and their associated metadata JSON, which are the core pieces of information your agent uses for retrieval.

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