How to Use the NinjaCat MCP in LlamaIndex

Q: How do I load NinjaCat tools into my LlamaIndex application?

Install llama-index-tools-mcp. Set up a BasicMCPClient connected to the NinjaCat MCP Server, then wrap it in an McpToolSpec to pass to your FunctionAgent.

Q: Can LlamaIndex search the contents of a NinjaCat report?

The server provides the metadata and the link via getreportdownloadurl. Your LlamaIndex app needs to download the file from that link and parse it to index the actual contents.

Q: How do I index my active campaigns using the MCP server?

Run listagencycampaigns through your agent. Take the resulting JSON array and convert those campaign records into LlamaIndex Document objects for embedding.

Q: Will my LlamaIndex agent hallucinate advertiser details with NinjaCat?

No. By providing the listadvertisers and getadvertiser tools, the agent fetches hard data from the API to answer queries instead of guessing.

Index your NinjaCat marketing reports and agency data into LlamaIndex 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 NinjaCat MCP to LlamaIndex

Create your Vinkius account to connect NinjaCat 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 NinjaCat with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Agency Configurations

The `get_agency_info` and `list_advertisers` tools feed your agency's structural data directly into a LlamaIndex vector store. Instead of asking a generic model about your setup, your RAG application queries the actual indexed list of your clients. You pull specific details using `get_advertiser` and embed that text. When a user asks which clients run active campaigns, LlamaIndex searches the embedded tool outputs and returns an answer grounded in your real NinjaCat data.

Map Data Sources to RAG Apps

Your LlamaIndex agent uses `list_data_sources` and `list_data_accounts` to understand exactly where your marketing metrics live. It indexes the connections so the system knows which Google Ads or Meta accounts belong to which advertiser. This means your RAG application understands the context of your data infrastructure. If an analyst queries the system about a specific ad account, the agent retrieves the exact data account ID from the index before attempting any further analysis.

NinjaCat MCP Server Report Search

Calling `list_reports` and `get_report_history` allows LlamaIndex to build a searchable timeline of your marketing outputs. The agent ingests the metadata about when reports ran, who they were for, and their status. When a user needs the actual file, the agent triggers `get_report_download_url`. You combine historical metadata search with live retrieval. You stop guessing where the monthly performance deck is and just ask your index.

Setup guide

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

Install `llama-index-tools-mcp`. Set up a `BasicMCPClient` connected to the NinjaCat MCP Server, then wrap it in an `McpToolSpec` to pass to your FunctionAgent.

The server provides the metadata and the link via `get_report_download_url`. Your LlamaIndex app needs to download the file from that link and parse it to index the actual contents.

Run `list_agency_campaigns` through your agent. Take the resulting JSON array and convert those campaign records into LlamaIndex Document objects for embedding.

No. By providing the `list_advertisers` and `get_advertiser` tools, the agent fetches hard data from the API to answer queries instead of guessing.

This integration touches sensitive marketing performance records and advertiser IDs via the MCP server. We secure this by routing the connection through a zero-trust, ephemeral environment where no data is logged or stored at rest.

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