How to Use the AdsWizz MCP in LlamaIndex

Q: How do I make the AdsWizz tools available to my LlamaIndex agent?

Use the McpToolSpec from the llama-index-tools-mcp package. You just point it to your Vinkius endpoint, and it generates the tools for your agent. It's the simplest way to add live API calls to your RAG application.

Q: Does LlamaIndex re-call the AdsWizz API for every query?

Not unless you want it to. Once data from a tool like listcampaigns is indexed, LlamaIndex can answer questions from that stored knowledge. You control how often the agent re-runs tools to get fresh data from the AdsWizz MCP server.

Turn your AdsWizz campaign data into a queryable knowledge base with LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AdsWizz MCP to LlamaIndex

Create your Vinkius account to connect AdsWizz 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 AdsWizz with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Live Campaign Performance

Your agent can call `get_audio_performance` and feed the results directly into a vector index. This creates a snapshot of your ad metrics. Now you can ask natural language questions about performance over time without hitting the API again. Your agent's knowledge is no longer ephemeral. The data pulled from the AdsWizz server becomes a persistent, searchable asset in your vector store. This grounds all future answers in historical fact, not just the latest API call.

Build a RAG App for Ad Inventory

Set up an agent to periodically run `list_zones` and `list_campaigns`. LlamaIndex will take the output—available ad slots and current campaign placements—and index it. This builds a searchable database of your advertising landscape. Now you can ask more complex questions. Try something like, "Show me tech podcasts in our inventory that aren't running the new product campaign." LlamaIndex finds the relevant indexed documents from past tool calls and synthesizes a direct answer.

Query Your AdsWizz MCP Server History

The `get_campaign` tool fetches detailed ad configurations. By indexing this output with LlamaIndex, you create a living document of your campaign strategies and setups over time. This means you can query your own strategic history. Ask your agent, "What was the targeting for the Q4 holiday campaign?" and get an answer based on the actual data pulled from the MCP server, not a guess or a hallucination.

Setup guide

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

Use the `McpToolSpec` from the `llama-index-tools-mcp` package. You just point it to your Vinkius endpoint, and it generates the tools for your agent. It's the simplest way to add live API calls to your RAG application.

Yes, that's the core strength of LlamaIndex. You can index the output from the AdsWizz tools right alongside PDFs, text files, or data from other APIs. This creates a single, unified knowledge base for your agent.

Not unless you want it to. Once data from a tool like `list_campaigns` is indexed, LlamaIndex can answer questions from that stored knowledge. You control how often the agent re-runs tools to get fresh data from the AdsWizz MCP server.

LlamaIndex doesn't just call the API; it structures the output for retrieval. It turns raw JSON from the AdsWizz server into a knowledge base you can search with plain English, connecting different pieces of information to answer complex questions.

The MCP server only touches your AdsWizz campaign and performance metrics. Your connection is authenticated by a single Vinkius token, so your direct AdsWizz credentials are never involved. All operations run in ephemeral, sandboxed environments that are destroyed after each request.

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