How to Use the Cognita (RAG Framework) MCP in OpenAI Agents SDK

Q: Why does my OpenAI Agents SDK throw tool validation errors?

Your guardrails might block the agent if it tries to run ingestdata with a malformed JSON payload. Make sure your agent's system prompt strictly defines the schemas required by the Cognita (RAG Framework) tools.

Feed your OpenAI Agents SDK production guardrails raw vector data directly from your Cognita (RAG Framework) pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cognita (RAG Framework) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Cognita (RAG Framework) 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 Cognita (RAG Framework) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Cognita RAG right inside OpenAI Agents SDK

The `rag_query` tool lets your OpenAI Agents SDK fetch precise vector arrays directly from your Cognita pipelines. Stop manually pasting context into your system prompts. If you want to dig deeper, the agent can call `search_chunks` to pull structured rules and active presets. This keeps your token usage low and stops your production agents from hallucinating when they don't have the facts.

Trace cloud payload IDs on the OpenAI dashboard

The `get_collection` tool maps your backend traces directly to the OpenAI telemetry dashboard. The SDK handles the agent handoffs while this tool maps the backend. Pair that with `list_collections` to trace bounded routing spaces. This MCP Server lets you audit exactly which data chunk your agent accessed during a complex run.

Direct ingestion for multi-agent workflows

The `ingest_data` tool provisions highly-available JSON payloads when your agent receives new raw text. This happens in the background, keeping your OpenAI Agents SDK loop fast and focused. Your agent can also inspect the active buckets driving your storage by calling `list_data_sources`. It handles the file structure so you don't have to write custom pipeline code.

Setup guide

Set up Cognita (RAG Framework) 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 Cognita (RAG Framework) tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK, spin up the Vinkius endpoint, and pass it to your Agent constructor using `MCPServerStreamableHttp`. The agent will auto-discover the tools and start querying your vector space immediately.

Yes, the SDK manages concurrent agent steps while this MCP Server handles the concurrent retrieval load. Each agent instance calls `rag_query` independently to pull context from your transformation vectors.

Your guardrails might block the agent if it tries to run `ingest_data` with a malformed JSON payload. Make sure your agent's system prompt strictly defines the schemas required by the Cognita (RAG Framework) tools.

You can filter the tools list before passing it to the Agent constructor. This MCP Server allows you to expose only `search_chunks` and omit the ingestion tools if you want a read-only setup.

Your data stays inside the Vinkius V8 isolate sandbox. The raw JSON payloads and cloud logging traces passing through this MCP Server are processed ephemerally and never saved on our servers.

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