How to Use the Emma MCP in LlamaIndex

Q: Can LlamaIndex query Emma member groups semantically?

Yes. Your LlamaIndex agent can run listgroups to pull all active segments, index their names and descriptions, and let you search for the right target group using natural language queries.

Q: Does LlamaIndex prevent hallucinations when reading Emma stats?

Yes. By using getmailingstats to inject raw, live numbers directly into the LLM's context window, LlamaIndex guarantees that campaign performance answers are grounded in real data.

Index live Emma campaign data into LlamaIndex vector stores using this managed 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 Emma MCP to LlamaIndex

Create your Vinkius account to connect Emma 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 Emma with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Grounding RAG in Emma Metrics

LlamaIndex takes the output of Emma tools like `get_mailing_stats` and indexes them directly into your vector database. This prevents your agent from hallucinating campaign performance numbers when you ask for recent trends. Your RAG pipeline queries actual, live statistics instead of relying on outdated training data. By feeding the results of `list_mailings` into your index, you create a searchable history of all sent campaigns. The agent can compare past open rates with current drafts, offering data-driven suggestions grounded in your actual marketing history.

LlamaIndex Semantic Search on Emma Data

Instead of just reading subscriber lists, LlamaIndex allows you to build a queryable knowledge base from your Emma audience. Your agent runs `list_members` and `list_fields` to construct semantic profiles of your customer segments, making it easy to search for specific user behaviors. When you query the index about subscriber demographics, the LlamaIndex agent pulls the latest records using `get_member`. This ensures your marketing decisions are always backed by live, structured data rather than static snapshots.

Context-Aware Automation Auditing

This MCP server enables LlamaIndex to retrieve and evaluate your active email workflows on demand. By calling `list_automations` and `list_webhooks`, your agent builds a complete map of your active triggers and indexes them for compliance checks. You can ask the agent to identify redundant triggers or find gaps in your customer journey. The tool outputs are parsed, indexed, and evaluated against your internal guidelines to keep your marketing operations clean.

Setup guide

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

Install llama-index-tools-mcp and initialize the BasicMCPClient with your Vinkius URL. Then, convert the Emma tools to a tool spec using McpToolSpec and pass them to your agent.

Yes. Your LlamaIndex agent can run list_groups to pull all active segments, index their names and descriptions, and let you search for the right target group using natural language queries.

Yes. By using get_mailing_stats to inject raw, live numbers directly into the LLM's context window, LlamaIndex guarantees that campaign performance answers are grounded in real data.

Yes. When setting up the tool spec, you can use the allowed tools filter to restrict your agent to read-only tools like list_mailings while blocking destructive actions.

The server processes subscriber records and custom fields from list_fields inside a zero-trust V8 sandbox. LlamaIndex only indexes the data you explicitly query, ensuring sensitive PII remains protected and ephemeral.

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