How to Use the MRPLN MCP in LlamaIndex

Q: Can I use LlamaIndex to create a searchable index of my MRPLN customers?

Yes. You use the McpToolSpec to load the MRPLN tools, then build a VectorStoreIndex from the output of tools like listcustomers. This makes your customer data queryable with natural language.

Q: Is it possible to query MRPLN tactic performance history with LlamaIndex?

Absolutely. You'd create an agent that periodically calls gettacticperformance for all your tactics and indexes the results. Your query engine can then analyze this indexed data to spot trends over time.

Ground your LlamaIndex RAG apps in live MRPLN production data, not just static documents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MRPLN MCP to LlamaIndex

Create your Vinkius account to connect MRPLN 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 MRPLN with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Your Customer Base in Plain English

This toolset lets you turn your customer list into a searchable knowledge base. Your LlamaIndex agent can periodically run `list_customers` and ingest all the records into a vector index. It's no longer just a static list of contacts. Now you can ask complex questions like, "Show me all leads in Arizona we haven't contacted this quarter." The query engine will synthesize an answer grounded in the actual data pulled from the `list_customers` tool, not a guess.

Analyze Historical Campaign Performance

Build an index of what works. Your agent can call `list_tactics` and `get_tactic_performance` on a schedule, feeding the results directly into a LlamaIndex vector store. This creates a living history of your campaign effectiveness. Instead of running new API calls every time, you can just query your index. Ask things like, "What was our most effective SMS tactic for new steel fabrication clients in Q2?" and get an immediate, data-backed answer from past results.

Build Grounded Customer Service with LlamaIndex

Give your support bots real-time data. A LlamaIndex query engine built on this MCP server can handle customer questions with up-to-the-minute accuracy. When a customer asks for an update, the agent queries its index for historical context. Then, it can call `get_customer` for live details and use `send_email_message` to send a complete, accurate response. It's a RAG application powered by your actual MRPLN operational data, which means fewer mistakes.

Setup guide

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

Yes. You use the `McpToolSpec` to load the MRPLN tools, then build a `VectorStoreIndex` from the output of tools like `list_customers`. This makes your customer data queryable with natural language.

LlamaIndex can use the MCP tools in two ways: to ingest data into an index for later querying, or to call a tool live as part of a query itself. This gives you a mix of historical context and real-time information.

Absolutely. You'd create an agent that periodically calls `get_tactic_performance` for all your tactics and indexes the results. Your query engine can then analyze this indexed data to spot trends over time.

The server provides a full set of tools for customer management. You get `create_customer`, `get_customer`, `list_customers`, and `update_customer` to handle the entire lifecycle of a customer record.

Your customer records and performance metrics are only accessed when your agent calls a tool. Vinkius isolates each session and all authentication is handled by a single, short-lived MCP token. The security of your indexed data depends on your own vector database's configuration.

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