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

Q: How do I configure the Craft (Docs & Notes) MCP Server for LlamaIndex?

Run pip install llama-index-tools-mcp. Set up a BasicMCPClient with your Vinkius URL. Pass that client to McpToolSpec and convert it using totoollistasync() before handing it to your FunctionAgent.

Q: Can LlamaIndex update my Craft (Docs & Notes) pages?

Yes, the updatedocument tool mutates global web context boundaries to substitute explicit document values. Your agent can correct outdated information in your notes after checking it against a newer source.

Q: Will LlamaIndex ingest my entire Craft (Docs & Notes) workspace?

Only if you tell it to. You can use the allowedtools filter in your setup to restrict access. If you only want it reading daily notes, just expose the getdailynote tool to the agent.

Q: How does the search tool work with vector databases?

The searchdocuments tool executes static listing mapping via text queries natively in the app. You can use this as a pre-filter before pulling full documents into your LlamaIndex vector store for deeper semantic processing.

Index your Craft documents into searchable vector stores using LlamaIndex and this dedicated 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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Craft pages into LlamaIndex knowledge bases

The `list_documents` tool identifies bounded routing spaces inside your workspace. Your LlamaIndex application calls this to discover every available page before deciding what to ingest. It grabs the raw IDs and prepares the ingestion pipeline automatically. Fetching the actual text requires the `get_document` tool. It retrieves explicit UX logging and traces document IDs directly into your memory store. You can run a nightly cron job that pulls your updated notes and embeds them into your vector database for accurate semantic search later.

Ingest specific blocks via MCP Server

Enumerating explicitly attached structured rules happens through the `list_blocks` tool. Instead of dumping an entire massive page into a single vector, LlamaIndex can chunk the data block by block. This keeps your embedding context tight and highly relevant. If the agent needs to add a summary back into the workspace, it calls `append_block`. The RAG application synthesizes answers from your past notes and injects the conclusion right below your original text. You get AI-generated insights grounded strictly in your own writing.

Query your checklists and daily logs

The `get_daily_note` tool retrieves elaborate mapping properties limiting daily pages. You can ask your LlamaIndex agent what you worked on last Tuesday. It pulls that specific daily log, embeds it on the fly, and answers based on the actual text you wrote that day. Gathering mapped checklists is handled by `list_tasks`. Your knowledge base now knows exactly which tasks remain open across your entire workspace. You stop guessing about project status because the agent queries the live checkmarks directly.

Setup guide

Set up Craft (Docs & Notes) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Craft (Docs & Notes) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Craft (Docs & Notes) tools.",
)
response = await agent.run("List recent Craft (Docs & Notes) data")

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 LlamaIndex

Run `pip install llama-index-tools-mcp`. Set up a `BasicMCPClient` with your Vinkius URL. Pass that client to `McpToolSpec` and convert it using `to_tool_list_async()` before handing it to your `FunctionAgent`.

Yes, the `update_document` tool mutates global web context boundaries to substitute explicit document values. Your agent can correct outdated information in your notes after checking it against a newer source.

Only if you tell it to. You can use the `allowed_tools` filter in your setup to restrict access. If you only want it reading daily notes, just expose the `get_daily_note` tool to the agent.

The `search_documents` tool executes static listing mapping via text queries natively in the app. You can use this as a pre-filter before pulling full documents into your LlamaIndex vector store for deeper semantic processing.

Vinkius processes your private checklists, daily reflections, and structural blocks through a zero-trust V8 sandbox. We never log the contents of your documents. The MCP server exists only for the duration of the API request and vanishes immediately after.

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