How to Use the Nuclino MCP in OpenAI Agents SDK

Q: How do I prevent an OpenAI Agents SDK tool call from deleting my Nuclino items?

The deleteitem tool is designed with a strict confirmation requirement. The MCP Server handles safety by requiring explicit verification, keeping your Nuclino workspaces safe from automated deletion loops.

Q: Does this integration support searching across multiple workspaces?

Yes, searchitems executes an indexed semantic search globally across your entire Nuclino team. Your agent can run this tool to locate unknown UUIDs without needing to manually loop through every single workspace.

Let your OpenAI Agents SDK coordinate multi-agent handoffs to write, read, and organize your Nuclino team wiki automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nuclino MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Wiki Management with OpenAI Agents SDK

`list_teams` bootstraps your team discovery process, letting your agent map root organizational units before drilling down into workspaces. From there, specialized agents use `list_workspaces` to locate the exact documentation targets. The OpenAI Agents SDK runs these discovery tools with built-in guardrails, preventing agents from wandering into unauthorized workspaces. You get a clear execution trace in your OpenAI dashboard showing exactly which workspace UUIDs were queried and when.

Safe Real-Time Document Mutations

`create_item` builds a brand new wiki page in your workspace with a direct Markdown payload, while `update_item` modifies existing documentation on the fly. These tools let your agent write release notes, update project specs, or draft meeting minutes directly into Nuclino. Because document destruction is irreversible, this MCP Server requires explicit user confirmation before executing `delete_item`. This safety gate prevents your agent from accidentally nuking critical corporate knowledge during automated cleanup tasks.

Graph-Based Knowledge Retrieval

`list_collections` maps the visual document relationship graph inside your workspace so your agent understands how pages connect. This lets the agent trace paths through nested folders and locate orphans or outdated resources. When the agent needs specific content, it pairs this structural map with `get_item` to grab the raw Markdown payload. It can also call `list_files` to locate binary attachments tied directly to those pages, making it easy to audit your files.

Setup guide

Set up Nuclino 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 Nuclino tools at runtime.
3

Create your Agent

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

Run the agent

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

You pass your Vinkius MCP Server HTTP URL directly to the SDK initialization block. The platform handles the underlying API key mapping, so your Python agents only need a single endpoint token to execute tools like `list_teams`.

Yes, you can route different tasks to specialized agents. For example, a writer agent can draft content using `create_item`, then hand off to an auditor agent that verifies taxonomy fields using `list_fields`.

The `delete_item` tool is designed with a strict confirmation requirement. The MCP Server handles safety by requiring explicit verification, keeping your Nuclino workspaces safe from automated deletion loops.

Yes, `search_items` executes an indexed semantic search globally across your entire Nuclino team. Your agent can run this tool to locate unknown UUIDs without needing to manually loop through every single workspace.

Your Markdown payloads and workspace UUIDs stay within an ephemeral V8 sandbox hosted by Vinkius. The MCP Server operates under a zero-trust model, meaning your wiki content is processed on demand and never stored 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