How to Use the Craft (Docs & Notes) MCP in AutoGen

Q: How do I register the Craft (Docs & Notes) MCP Server in AutoGen?

Install autogen-extmcp. Call mcpservertools with a StreamableHttpServerParams object containing your Vinkius URL. Pass the resulting tool list directly into your AssistantAgent constructor.

Q: Can multiple AutoGen agents edit the same Craft (Docs & Notes) page?

Yes. Any agent holding the tools can call updatedocument. You should design your conversation flow so a single designated writer agent handles the actual API calls to avoid race conditions.

Q: How does AutoGen search my Craft (Docs & Notes) workspace?

The searchdocuments tool executes static listing mapping via text queries. An agent can run a search, paste the matching document IDs into the chat, and ask the group which one it should investigate further.

Give your AutoGen multi-agent squads the ability to read, debate, and edit your Craft workspaces via this MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Craft (Docs & Notes) MCP to AutoGen

Create your Vinkius account to connect Craft (Docs & Notes) 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 Craft (Docs & Notes) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Agents debate and draft Craft pages

The `create_document` tool provisions highly-available JSON payloads to generate new document rows. Your AutoGen setup can feature a researcher agent and a writer agent. They argue over the collected facts until they reach a consensus, at which point the writer agent finally commits the agreed-upon text to a new page. Mutating global web context boundaries happens via the `update_document` tool. If a reviewer agent finds a flaw in the draft, it instructs the writer to fix it. The writer substitutes the explicit document values, creating a self-correcting editorial loop right inside your workspace.

Delegate checklist updates via MCP Server

Gathering mapped checklists requires the `list_tasks` tool. A project manager agent pulls every open task from your workspace. It then delegates those items to specialized worker agents in the chat group based on the task description. Deleting outdated information relies on the `delete_document` tool. A cleanup agent can propose vaporizing explicit app nodes that haven't been touched in months. A supervisor agent must approve the action before the deletion actually executes, preventing accidental data loss.

Analyze daily notes with AutoGen squads

Retrieving elaborate mapping properties limiting daily pages is the job of the `get_daily_note` tool. You can build a daily standup squad. One agent pulls your note from yesterday, while another agent critiques your productivity and suggests focus areas for today. The `list_blocks` tool enumerates explicitly attached structured rules exporting active blocks. Agents can read specific sections of a massive document without losing context. They parse the blocks, debate the structure, and use `append_block` to inject missing arguments into the outline.

Setup guide

Set up Craft (Docs & Notes) 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 Craft (Docs & Notes) 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="Craft (Docs & Notes)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Craft (Docs & Notes) 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="Craft (Docs & Notes)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Craft (Docs & Notes) 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 Craft. 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 Craft (Docs & Notes) 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 Craft (Docs & Notes) MCP in AutoGen

Install `autogen-ext[mcp]`. Call `mcp_server_tools` with a `StreamableHttpServerParams` object containing your Vinkius URL. Pass the resulting tool list directly into your `AssistantAgent` constructor.

Yes. Any agent holding the tools can call `update_document`. You should design your conversation flow so a single designated writer agent handles the actual API calls to avoid race conditions.

The `search_documents` tool executes static listing mapping via text queries. An agent can run a search, paste the matching document IDs into the chat, and ask the group which one it should investigate further.

Yes. You only need an outbound internet connection to hit the Vinkius endpoint. The `McpToolAdapter` handles all the schema conversions between your local Python environment and the remote endpoint natively.

Vinkius handles authentication natively and runs the connection in an isolated V8 sandbox. Your sensitive daily notes, private task lists, and draft documents are never stored on our infrastructure. The MCP session dies the moment the agent finishes its tool call.

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