How to Use the MOBIDI MCP in LlamaIndex

Q: How does the MOBIDI integration with LlamaIndex prevent hallucinations?

It indexes live data from tools like getrecordbyid directly into your vector store. Your agent answers questions using actual campaign records instead of guessing.

Q: Can I use MOBIDI tools to build a RAG pipeline in LlamaIndex?

Yes. You convert tools like executereport into indexable data sources. The agent queries the API, indexes the output, and retrieves it to answer performance questions.

Index mobile ad performance data and campaign records directly into LlamaIndex vector stores for semantic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MOBIDI MCP to LlamaIndex

Create your Vinkius account to connect MOBIDI 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 MOBIDI with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live ad campaign data into your knowledge base

Stop relying on static spreadsheets for your ad ops. This MCP Server lets your LlamaIndex pipeline query live campaign data using `list_records` and convert the raw JSON into vector nodes. Your RAG applications can now search real-time bidding parameters alongside your internal documentation. By pulling specific entries with `get_record_by_id`, the agent feeds fresh context into the index. This ensures your synthesis queries are always grounded in actual, live campaign states rather than outdated exports.

Query MOBIDI reports with semantic search in LlamaIndex

Finding the right performance metric should not require custom SQL. This MCP Server lets your LlamaIndex agent use `list_reports` to locate relevant data structures and then call `execute_report` to fetch the raw numbers. The output is parsed and indexed immediately. If your agent needs to check the structure of a specific metric file, it calls `get_report`. This lets you build RAG setups where users ask plain-English questions about app install trends and get answers backed by live API data.

Keep campaign databases clean and organized

Redundant targeting groups ruin your performance metrics. Your agent can call MCP tools like `get_record_count` to monitor database growth and flag anomalies. If it finds duplicate or stale profiles, it can execute `delete_record` to clean up the workspace. You can also map out the entire system architecture using `get_services` and `list_entity_types`. This gives your LlamaIndex agent a complete map of the data structure, making its semantic queries highly accurate.

Setup guide

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

It indexes live data from tools like `get_record_by_id` directly into your vector store. Your agent answers questions using actual campaign records instead of guessing.

Yes. You convert tools like `execute_report` into indexable data sources. The agent queries the API, indexes the output, and retrieves it to answer performance questions.

Install the MCP tool spec package, initialize the client, and convert the tools using the helper method. You can then pass them directly to your FunctionAgent.

Yes. The agent can modify bidding parameters and targeting criteria by invoking `update_record` when performance metrics drop below your target threshold.

Yes. All API credentials and bidding records are stored securely in Vinkius's zero-trust infrastructure. Your raw campaign data is never used for model training.

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