How to Use the Moloco MCP in LlamaIndex
Index your live Moloco performance metrics into LlamaIndex for grounded, data-driven AI responses.
Works with every AI agent you already use
…and any MCP-compatible client
Connect Moloco MCP to LlamaIndex
Create your Vinkius account to connect Moloco 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.
Grounded Ad Data Indexing
Convert output from `get_analytics_report` into a searchable vector index. Your agent uses this historical data to answer questions instead of guessing. This creates a knowledge base built on your actual account performance. You get answers rooted in real numbers rather than generic observations.
Query Campaigns with LlamaIndex
Ask questions about your account structure using `list_campaigns` and `list_ad_groups`. The system retrieves the exact campaign details you need for your RAG pipeline. This allows for complex queries across your entire ad account. You can pinpoint specific performance drivers by searching through your indexed data.
Unified Data Access
Combine your live API data with your existing documents into a single searchable index. The MCP Server acts as the bridge for real-time information. This gives your agent a complete view of your marketing assets and performance. It makes querying across different data types simple and fast.
Set up Moloco MCP in LlamaIndex
Prerequisites
- Python 3.10+ installed
-
llama-index-tools-mcppackage - 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 providesBasicMCPClientandMcpToolSpec. - 2
Connect with BasicMCPClient
Point
BasicMCPClientto 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 Moloco MCP tools into nativeFunctionToolobjects that any LlamaIndex agent can use. - 4
Run with any LLM
Create a
FunctionAgentwith the tools and your preferred LLM. SwapOpenAIforAnthropic,Gemini, or any LlamaIndex-supported provider.
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 Moloco tools.",
)
response = await agent.run("List recent Moloco data") Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Moloco. 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.
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 Moloco MCP in LlamaIndex
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the Moloco MCP today
We host it, we monitor it, we maintain it. You just paste one token.