How to Use the Nuclino MCP in AutoGen

Q: How do AutoGen agents collaborate on a Nuclino document?

One AutoGen agent can retrieve the document using getitem, draft modifications, and present them to a reviewer agent. Once approved, a third agent executes updateitem to push the finalized markdown to your Nuclino workspace.

Q: Can AutoGen agents search Nuclino workspaces to resolve debates?

Yes, AutoGen agents can run searchitems to find existing pages and verify facts during their conversation. This prevents agents from creating duplicate pages or operating on outdated information in Nuclino.

Q: How does AutoGen handle permission boundaries in Nuclino?

The AutoGen framework uses listworkspaces to identify isolated workspace boundaries before initiating any write operations. This ensures that agents only debate and modify content within authorized Nuclino workspaces.

Q: What transport does this MCP Server use to connect to AutoGen?

It connects via Streamable HTTP using the mcpservertools adapter in AutoGen to access Nuclino. This handles the schema translation automatically, letting your agents call tools without custom JSON parsing.

Q: Is my Nuclino user directory data safe with AutoGen?

Yes, user identities retrieved via listusers are processed locally within your secure AutoGen runtime environment. The Vinkius MCP Server sandbox ensures that sensitive team profiles and email addresses are never cached or leaked.

Let your AutoGen agents debate and coordinate updates to your Nuclino workspaces using consensus-driven tool execution.

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 AutoGen

Create your Vinkius account to connect Nuclino to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Nuclino wiki edits through AutoGen debate

The `create_item` tool triggers real-time replication to create permanent wiki documentation once your AutoGen agents reach consensus. A writer agent drafts the markdown content while an editor agent reviews the structure, ensuring only polished documentation is written to your Nuclino workspace. This MCP Server allows agents to debate the formatting and accuracy of the content before executing the final tool call. This collaborative loop prevents messy or incomplete pages from cluttering your Nuclino wiki.

Safely manage Nuclino document deletion in AutoGen

The `delete_item` tool requires heavy confirmation before destroying any structural wiki page due to its irreversible nature. In an AutoGen setup, a dedicated safety agent intercepts any delete requests and debates the necessity of the destruction with the requesting agent before touching Nuclino. This multi-agent verification layer acts as a guard against rogue code or accidental triggers in your AutoGen workflows. The deletion only executes in Nuclino when both agents agree and a final human-in-the-loop signal is received.

Enumerate team members using this MCP Server

The `list_users` tool enumerates the human identities attached globally to a team so your AutoGen agents can assign tasks or document ownership. Your coordinator agent checks this user directory to tag the correct team members in newly created Nuclino wiki pages. By mapping actual human profiles to Nuclino workspace items, your AutoGen agents can route notifications accurately. It bridges the gap between your automated agent conversations and your real-world team structure.

Setup guide

Set up Nuclino MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Nuclino tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Nuclino_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Nuclino data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Nuclino_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Nuclino data")
    print(result.messages[-1].content)

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 AutoGen

One AutoGen agent can retrieve the document using `get_item`, draft modifications, and present them to a reviewer agent. Once approved, a third agent executes `update_item` to push the finalized markdown to your Nuclino workspace.

Yes, AutoGen agents can run `search_items` to find existing pages and verify facts during their conversation. This prevents agents from creating duplicate pages or operating on outdated information in Nuclino.

The AutoGen framework uses `list_workspaces` to identify isolated workspace boundaries before initiating any write operations. This ensures that agents only debate and modify content within authorized Nuclino workspaces.

It connects via Streamable HTTP using the `mcp_server_tools` adapter in AutoGen to access Nuclino. This handles the schema translation automatically, letting your agents call tools without custom JSON parsing.

Yes, user identities retrieved via `list_users` are processed locally within your secure AutoGen runtime environment. The Vinkius MCP Server sandbox ensures that sensitive team profiles and email addresses are never cached or leaked.

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