How to Use the Adikteev MCP in LlamaIndex

Q: How do I set up the Adikteev tools in LlamaIndex?

Install the llama-index-tools-mcp package and create a BasicMCPClient pointing to your Vinkius endpoint. Pass that client to McpToolSpec, and then call totoollistasync() to get the functions for your agent.

Q: Can I ask my LlamaIndex agent questions about Adikteev campaign performance?

Yes. After your agent uses the getreporting tool, the campaign data is added to your index. You can then ask questions like "What was the CPA for my last retargeting campaign?" and get an answer grounded in your actual Adikteev data.

Q: How do I limit which Adikteev tools my agent can use?

When you initialize the agent, you can use the allowedtools filter. This lets you give an agent access to only getreporting, for example, preventing it from accidentally creating new segments.

Turn your Adikteev campaign data into a queryable knowledge base for your LlamaIndex RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adikteev MCP to LlamaIndex

Create your Vinkius account to connect Adikteev 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 Adikteev with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Marketing Segments

Use these tools to pull Adikteev data and index it for real-time querying. When your agent calls `list_segments` or `create_segment`, LlamaIndex doesn't just get the data once. It adds the segment's name, ID, and creation date to a vector store. Now you can ask natural language questions against your own marketing history. Queries like "Show me all the segments I created last month for Android users" get answered using the actual data fetched from the Adikteev API, not a guess.

Track Churn and Performance Over Time

The `get_churn_scores` and `get_reporting` tools feed directly into your knowledge base. Each time you run them, the results are indexed, building a historical record of user risk and campaign performance inside your LlamaIndex application. This means you can query trends. Ask your RAG agent, "What was the average churn score for the 'Q2 Power Users' segment in May?" and it can synthesize an answer by looking at the indexed history of tool outputs. It's a living record of your marketing efforts.

A LlamaIndex ToolSpec for Adikteev

This MCP Server provides the tools you need to build a knowledge-augmented marketing agent. The five functions for managing segments, getting reports, and checking churn scores are exposed through a `McpToolSpec` that's easy to integrate. After you install the package, you create a client and pass it to the `McpToolSpec`. This gives your LlamaIndex agent the ability to call the Adikteev API. The agent uses the tools to answer questions, and the results are automatically fed into your index for future queries.

Setup guide

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

Install the `llama-index-tools-mcp` package and create a `BasicMCPClient` pointing to your Vinkius endpoint. Pass that client to `McpToolSpec`, and then call `to_tool_list_async()` to get the functions for your agent.

Yes. After your agent uses the `get_reporting` tool, the campaign data is added to your index. You can then ask questions like "What was the CPA for my last retargeting campaign?" and get an answer grounded in your actual Adikteev data.

Yes, that's what it's for. You can index Adikteev API results alongside your own marketing strategy docs, PDFs, and notes. When you ask a question, LlamaIndex queries both the live API data and your static documents to give a complete answer.

When you initialize the agent, you can use the `allowed_tools` filter. This lets you give an agent access to only `get_reporting`, for example, preventing it from accidentally creating new segments.

The server itself is stateless; it only proxies requests. Any Adikteev data like audience segment definitions or campaign performance metrics is handled by the LlamaIndex framework. You control where your index is stored, so the data stays in your environment.

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