How to Use the Nuclino MCP in LlamaIndex

Q: How does LlamaIndex index Nuclino workspace documents?

LlamaIndex uses listitems to gather document UUIDs and then calls getitem to pull the raw markdown. This content is chunked and embedded directly into your LlamaIndex vector store for semantic search.

Q: Can I search across Nuclino fields using LlamaIndex filters?

Yes, you can call listfields to retrieve your team's custom properties and map them as metadata filters in LlamaIndex. This lets your agent execute highly precise vector queries restricted to specific Nuclino document types.

Q: Does this MCP Server support real-time indexing of new Nuclino pages in LlamaIndex?

Your LlamaIndex pipeline can periodically run searchitems to detect newly edited pages or updates in Nuclino. Once found, it pulls the fresh markdown and updates your vector index instantly.

Q: How does LlamaIndex handle document hierarchies in Nuclino?

The LlamaIndex agent calls listcollections to map out the visual grouping directories of your Nuclino workspace. It then attaches these collection relationships as metadata tags to your indexed documents.

Index your Nuclino wiki pages into LlamaIndex vector stores to ground your agent's answers in live workspace data.

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 LlamaIndex

Create your Vinkius account to connect Nuclino 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 Nuclino with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Nuclino markdown directly into RAG pipelines

The `get_item` tool retrieves the exact markdown payload and configuration of a specific Nuclino page to feed your LlamaIndex document ingestors. This live data is parsed and loaded into your vector index, ensuring your agent queries real-time wiki content instead of stale static files. Using this MCP Server, your LlamaIndex RAG pipeline preserves headers, lists, and formatting. Your agent then retrieves highly accurate context blocks from Nuclino to answer user queries with zero hallucination.

Query live Nuclino attachment metadata with LlamaIndex

The `list_files` tool exposes pure URL bindings mapping binary data records back to object storage for your LlamaIndex indexing pipelines. LlamaIndex reads these file paths, allowing your agent to reference and catalog physical attachments bolted onto your wiki pages. This capability lets your LlamaIndex index track not just text, but the exact locations of design files, PDFs, and images inside Nuclino. Your agent can point users to the precise attachment they need during conversational search.

Map taxonomy dimensions using this MCP Server

The `list_fields` tool maps customizable structured property fields globally binding a team to help your LlamaIndex agent understand your Nuclino metadata taxonomy. The agent uses these fields to filter search queries and target specific document categories during vector retrieval. By aligning your LlamaIndex index metadata with actual Nuclino workspace fields, you get highly targeted retrieval. Your agent avoids scanning irrelevant workspaces by filtering queries based on these native property dimensions.

Setup guide

Set up Nuclino 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 Nuclino 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 Nuclino tools.",
)
response = await agent.run("List recent Nuclino 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 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 LlamaIndex

LlamaIndex uses `list_items` to gather document UUIDs and then calls `get_item` to pull the raw markdown. This content is chunked and embedded directly into your LlamaIndex vector store for semantic search.

Yes, you can call `list_fields` to retrieve your team's custom properties and map them as metadata filters in LlamaIndex. This lets your agent execute highly precise vector queries restricted to specific Nuclino document types.

Your LlamaIndex pipeline can periodically run `search_items` to detect newly edited pages or updates in Nuclino. Once found, it pulls the fresh markdown and updates your vector index instantly.

The LlamaIndex agent calls `list_collections` to map out the visual grouping directories of your Nuclino workspace. It then attaches these collection relationships as metadata tags to your indexed documents.

Your markdown text and workspace metadata are processed inside an ephemeral V8 sandbox. The connection uses single-token authorization to stream data directly to your local LlamaIndex vector store without exposing it to third parties.

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