How to Use the Directus MCP in OpenAI Agents SDK

Q: How do I connect the Directus MCP Server to my OpenAI Agents SDK pipeline?

Install the SDK, then initialize the connection using MCPServerStreamableHttp with your Vinkius endpoint. Pass this server instance in the mcpservers list when instantiating your Agent to let it automatically discover tools like listitems.

Q: Does this integration support file management?

Yes. Your agent can read and organize media assets using getfile and listfiles. This lets you build agents that link uploaded media directly to database records.

Build production-grade Python agents that query and modify your Directus database with 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 Directus MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe Database Writes with OpenAI Agents SDK

The OpenAI Agents SDK executes database changes safely by running your Directus schema operations through structured guardrails. Your agent uses `create_item` and `update_item` to modify records while the SDK validates the payload against your live database rules before committing the transaction. If a model attempts an invalid write, the SDK halts execution and prompts for human approval or triggers a safe agent handoff. This prevents corrupted database entries and ensures your relational integrity remains intact.

Automated Schema Discovery via MCP Server

This MCP Server exposes your entire database structure directly to OpenAI agents without manual API mapping. The agent calls `list_collections` and `list_fields` to inspect your tables on the fly, building its own context of your data model. Because the schema is discovered dynamically, you can add tables or fields in Directus and your agent immediately understands how to query them. No code redeployments or prompt updates required.

Step-by-Step Activity Tracing

Monitor exactly how your Python agents interact with your content using OpenAI's developer dashboard. Every call to `list_activity` or `get_item` is logged with execution times and token usage, giving you full visibility into agent behavior. When debugging complex agent handoffs, these traces show you the exact parameters passed to `search_items` or `delete_item`. You pinpoint slow queries and bad model assumptions in seconds.

Setup guide

Set up Directus 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 Directus tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK, then initialize the connection using `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this server instance in the `mcp_servers` list when instantiating your Agent to let it automatically discover tools like `list_items`.

Yes, you control access by configuring the API token roles inside Directus. When the agent calls `list_roles` or attempts to run `update_item`, the server enforces your database-level permissions.

You can design specialized agents where one drafts content using `create_item` and another reviews it. The SDK handles the state handoff, ensuring each agent only calls the specific tools it needs.

Yes. Your agent can read and organize media assets using `get_file` and `list_files`. This lets you build agents that link uploaded media directly to database records.

Vinkius hosts the MCP server in a zero-trust, ephemeral V8 Isolate sandbox. Your database tokens and records fetched via `get_item` never persist on our platform, keeping your operational data isolated.

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