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

Q: How do I connect the Craft (Docs & Notes) MCP Server to LangChain?

Install langchain-mcp-adapters and langgraph. Initialize a MultiServerMCPClient pointing to your Vinkius endpoint URL. Call client.gettools() and pass the returned array to your agent constructor.

Q: Can LangChain agents search my Craft (Docs & Notes) workspace?

Yes, the searchdocuments tool executes static text queries. The agent parses the search results to find specific document IDs. It then decides which document to read fully based on relevance.

Q: Does the server support deleting pages?

The deletedocument tool drops live document rows entirely. This action is irreversible. Write strict system prompts if you give an autonomous agent access to this specific tool.

Build multi-step reasoning pipelines that read and write your Craft workspaces directly through the LangChain MCP integration.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Craft document creation into LangChain

The `create_document` tool provisions new JSON payloads to generate rows inside your Craft workspace. Your LangChain agent can take research gathered from previous chain steps and format it straight into a new Craft page. We built this so you don't have to write custom API wrappers just to dump text into your notes. Once the page exists, the agent uses `update_document` to mutate global context boundaries and insert fresh data. LangSmith traces every single call natively. You get full visibility into latency and token usage when your agent decides to mutate those document values.

Inject structural blocks via MCP Server

Executing `append_block` performs structural injection of properties driving new blocks inside an existing Craft node. ReAct agents excel here because they can read the current structure first. They look at the output, decide where the new information fits best, and fire the tool. Reading the current state requires the `list_blocks` tool. It enumerates explicitly attached structured rules exporting active blocks. Your pipeline pulls those blocks, analyzes the content, and appends the next logical section without overwriting your manual edits.

Extract daily tasks for agent evaluation

Retrieving elaborate mapping properties limiting daily pages happens through the `get_daily_note` tool. You can wire up a morning routine chain that pulls your daily note, extracts the text, and passes it to a summarization prompt. The `list_tasks` tool gathers mapped checklists across your workspace. LangChain takes those raw tasks and feeds them to other APIs in the same chain. Your agent reads the boxes you checked in Craft and immediately triggers downstream actions based on that exact list.

Setup guide

Set up Craft (Docs & Notes) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Craft (Docs & Notes) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "craft-docs-notes-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Craft (Docs & Notes) transactions"
    })
    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 LangChain

Install `langchain-mcp-adapters` and `langgraph`. Initialize a `MultiServerMCPClient` pointing to your Vinkius endpoint URL. Call `client.get_tools()` and pass the returned array to your agent constructor.

Yes, the `search_documents` tool executes static text queries. The agent parses the search results to find specific document IDs. It then decides which document to read fully based on relevance.

LangSmith traces the exact tool input and output. You can see the exact JSON payload sent to `create_document`. Fix the schema mismatch in your prompt and replay the chain.

The `delete_document` tool drops live document rows entirely. This action is irreversible. Write strict system prompts if you give an autonomous agent access to this specific tool.

Vinkius runs the server in an ephemeral V8 Isolate Sandbox. Your personal daily logs, workspace checklists, and document texts never touch persistent storage on our end. The MCP connection shuts down the millisecond the API responds.

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