How to Use the Novu MCP in LlamaIndex

Q: How do I feed Novu subscriber lists into a LlamaIndex vector store?

Use the searchsubscribers tool to retrieve user profiles. LlamaIndex reads the resulting JSON array from this MCP server and converts it into document nodes for semantic indexing.

Q: Can a LlamaIndex query engine trigger a Novu broadcast?

Yes, you register triggerbroadcast as an available tool in your FunctionAgent. When a query requires a system-wide update, your LlamaIndex MCP client invokes the tool directly.

Q: How does LlamaIndex handle subscriber lookup errors in Novu?

If getsubscriber returns a missing ID, the framework catches the tool error. The query engine then prompts the user to create a profile or uses fallback logic.

Q: Can I manage topic subscriptions dynamically?

Yes, you use createtopicsubscriptions to add users to specific lists. This tool lets your agent organize subscribers based on their semantic query history.

Q: How does this server protect subscriber preferences from data leaks in LlamaIndex?

The server processes all preference payloads from bulkupdatesubscriberpreferences in a zero-trust, ephemeral V8 container. No subscriber preference data is saved to external storage, ensuring complete isolation during your MCP sessions.

Index active notification templates and subscriber data directly into your LlamaIndex knowledge bases.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Novu MCP to LlamaIndex

Create your Vinkius account to connect Novu 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 Novu with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index user preferences with LlamaIndex and Novu

The `get_subscriber_preferences` tool pulls current user settings directly into your vector store. LlamaIndex indexes these preferences semantically so your query engine knows exactly which channels are active before generating responses via the MCP server. If a user updates their settings, `update_subscriber_preference` writes those changes back to Novu immediately. This bidirectional sync prevents your RAG pipeline from generating alerts for channels the user disabled.

Query message histories semantically

The `list_messages` tool retrieves recent outbound alerts to populate your agent's memory. By indexing these messages, your RAG application can answer user questions about past alerts without querying a separate database. When users ask about missing alerts, the agent uses `get_topic_subscription` to check their delivery status. This grounding ensures the agent's answers match actual system logs instead of hallucinating delivery states.

Sync environment variables and setups

The `list_environment_variables` tool exposes your current configuration settings directly to your RAG pipeline. This MCP server lets your LlamaIndex agent verify active endpoints and configurations before executing complex notification workflows. For dynamic updates, `create_environment_variable` configures new parameters during runtime. This capability ensures your deployment pipelines match your live environment configurations.

Setup guide

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

Use the `search_subscribers` tool to retrieve user profiles. LlamaIndex reads the resulting JSON array from this MCP server and converts it into document nodes for semantic indexing.

Yes, you register `trigger_broadcast` as an available tool in your FunctionAgent. When a query requires a system-wide update, your LlamaIndex MCP client invokes the tool directly.

If `get_subscriber` returns a missing ID, the framework catches the tool error. The query engine then prompts the user to create a profile or uses fallback logic.

Yes, you use `create_topic_subscriptions` to add users to specific lists. This tool lets your agent organize subscribers based on their semantic query history.

The server processes all preference payloads from `bulk_update_subscriber_preferences` in a zero-trust, ephemeral V8 container. No subscriber preference data is saved to external storage, ensuring complete isolation during your MCP sessions.

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