How to Use the Notion MCP in LlamaIndex

Q: How do I load Notion data into LlamaIndex?

Use llama-index-tools-mcp to initialize the client, then convert the tools using McpToolSpec. Your agent can then call searchpages and getblocks to read and index page content dynamically.

Q: Can LlamaIndex update Notion properties after a search?

Yes, your agent can run updatepageproperties to modify tags or status fields based on search results. It uses searchdatabases to find the target database and then applies the updates.

Q: Does this Notion MCP Server support LlamaIndex filtering?

Yes, you can use the allowedtools filter in LlamaIndex to restrict the agent to read-only tools like getpage and querydatabase, blocking destructive tools like deleteblock.

Q: How does LlamaIndex handle deeply nested Notion blocks?

The agent uses getblocks recursively to traverse the block hierarchy. It reads paragraph, list, and heading blocks, building a clean textual representation for your index.

Index your Notion pages and databases into vector stores for grounded RAG using LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Notion MCP to LlamaIndex

Create your Vinkius account to connect Notion 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 Notion with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live Notion blocks for semantic search

This MCP Server connects LlamaIndex agents to your workspace via 14 tools like `get_blocks` and `search_pages`. The agent reads block-level text and loads it directly into your document indexes. Instead of processing static dumps, your RAG pipeline queries live Notion data. The agent runs `get_page` to retrieve properties, ensuring your index stays updated with real-time workspace changes.

Ground LlamaIndex agents in database schemas

Your LlamaIndex agent uses `get_database` and `query_database` to understand the exact structure of your tables before writing new entries. This prevents formatting errors when generating new rows. The agent acts as a database administrator, running `create_database` or `update_page_properties` based on semantic queries. It uses the actual schema definition to format raw text inputs into valid Notion property JSON.

Run RAG on Notion workspace users

By exposing `list_users` to your LlamaIndex pipeline, your agent maps workspace members to specific document changes. It matches user IDs with block updates retrieved via `get_blocks`. This MCP integration lets you build directories or audit trails. The agent queries user metadata to answer questions about who modified a page, combining identity data with page content.

Setup guide

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

Use `llama-index-tools-mcp` to initialize the client, then convert the tools using `McpToolSpec`. Your agent can then call `search_pages` and `get_blocks` to read and index page content dynamically.

Yes, your agent can run `update_page_properties` to modify tags or status fields based on search results. It uses `search_databases` to find the target database and then applies the updates.

Yes, you can use the `allowed_tools` filter in LlamaIndex to restrict the agent to read-only tools like `get_page` and `query_database`, blocking destructive tools like `delete_block`.

The agent uses `get_blocks` recursively to traverse the block hierarchy. It reads paragraph, list, and heading blocks, building a clean textual representation for your index.

Your Notion database rows and page texts flow through ephemeral V8 isolates running this MCP Server directly to your local LlamaIndex vector store. No workspace data is cached or stored on Vinkius servers.

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