How to Use the eSputnik MCP in LlamaIndex

Turn your eSputnik marketing data into a searchable knowledge base. Ask your LlamaIndex app questions, get answers from your own data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect eSputnik MCP to LlamaIndex

Create your Vinkius account to connect eSputnik 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 eSputnik with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Contacts for RAG

Give your LlamaIndex agent the tools to build a real-time index of your customer base. Your agent can periodically run `list_contacts` and `get_contact` to pull data from eSputnik. It then embeds and indexes this information into a vector store. Now you can ask questions in plain English, like "show me all contacts in the 'Power Users' group who joined last month." LlamaIndex retrieves the relevant contacts from its index and uses the LLM to synthesize an answer. It's not just data retrieval; it's data understanding.

Analyze Campaign Performance with LlamaIndex

This MCP server lets your agent ingest and analyze marketing outcomes. By calling `get_message_status` for recent campaigns and indexing the results, your agent builds a historical record of what works and what doesn't. You can then query this index to spot trends. Ask, "what was the open rate for the last three SMS campaigns sent via `send_smart_send`?" Your agent can pull the indexed status data and calculate the answer, grounding its response in actual performance metrics.

Create Dynamic Segments via Query

Combine LlamaIndex's query power with eSputnik's action tools. First, you ask your agent a complex question about your users, which it answers by querying its indexed knowledge of your contacts and groups. Based on the answer, the agent can formulate a plan. It can use `search_contacts` to get fresh IDs for the users it identified, then use `attach_to_group` to put them into a new, hyper-specific segment for a targeted campaign. Your natural language query just created a new marketing audience.

Setup guide

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

Yes. You'd configure your LlamaIndex agent to periodically run `list_contacts` and index them with a timestamp. When you ask the question, it will perform a vector search on its index for contacts within that date range.

You configure an ingestion pipeline. This is typically a scheduled job where your LlamaIndex application calls tools like `list_contacts` or `list_groups` and re-indexes the results. This keeps the knowledge base from getting stale.

Absolutely. That's the core idea of RAG. You index your product docs and the eSputnik contact data into the same vector store. Then you can ask questions that require both sources, like 'find contacts who might be interested in our new API feature'.

The MCP tool adapter will raise an error that LlamaIndex can catch. Good practice is to build retry logic into your ingestion pipeline or to log the failure so you know there's a gap in your indexed data.

You control where the index is stored. The eSputnik MCP server itself is stateless; it just retrieves the contact records and group lists for your agent. It's your responsibility to secure the vector database where LlamaIndex stores the indexed contact information.

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