How to Use the Kevel MCP in LlamaIndex

Q: How do I register the Kevel MCP tools with LlamaIndex?

Install llama-index-tools-mcp via pip. Set up a BasicMCPClient with your Vinkius URL, wrap it in McpToolSpec, and call await mcptoolspec.totoollistasync() to pass the tools to your FunctionAgent.

Q: Can LlamaIndex index all Kevel ad creatives at once?

It depends on your pagination limits. The listcreatives and listads tools fetch default batch sizes. You will need to build looping logic in your agent to paginate through massive creative libraries before embedding them.

Q: Does LlamaIndex support filtering which MCP Server tools to expose?

Yes. You can restrict the agent using the allowedtools parameter. If you only want it searching inventory, you can allow listsites and listzones while blocking access to advertiser data.

Index your live Kevel ad inventory into LlamaIndex via this MCP Server for semantic RAG queries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kevel MCP to LlamaIndex

Create your Vinkius account to connect Kevel 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 Kevel with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a searchable ad knowledge base

LlamaIndex treats your ad engine as a live data source. Instead of just returning API JSON, your RAG application can call `list_campaigns` and `list_flights` to index active delivery rules. This means you can query your current ad setup using natural language. The agent grounds its answers in actual inventory data. If a client asks what banner sizes are running, the system searches the indexed results from `list_ad_types` and `list_creatives` rather than guessing.

Semantic search for LlamaIndex MCP Server

Finding specific placements across a massive network is tedious. You can wire the `list_sites` and `list_zones` tools into your query engine to map out your exact ad real estate. The agent embeds these descriptions into your vector store. When sales asks for available native slots, the system retrieves the exact zone IDs. It completely removes the need to manually click through the management dashboard to find where specific ads can run.

Cross-reference advertisers with RAG

You can combine your internal sales documents with live platform data. The agent pulls specific client configurations via `get_advertiser` and `list_advertisers`, storing them alongside your PDF contracts or pricing sheets. This creates a unified query interface. Your team can ask about a client's active campaigns, and the system will pull the live status using `get_campaign` while simultaneously referencing the negotiated rates from your document index.

Setup guide

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

Install `llama-index-tools-mcp` via pip. Set up a `BasicMCPClient` with your Vinkius URL, wrap it in `McpToolSpec`, and call `await mcp_tool_spec.to_tool_list_async()` to pass the tools to your `FunctionAgent`.

It depends on your pagination limits. The `list_creatives` and `list_ads` tools fetch default batch sizes. You will need to build looping logic in your agent to paginate through massive creative libraries before embedding them.

Standard chatbots forget context. LlamaIndex embeds the output of your ad inventory queries into a vector store, allowing you to run semantic searches against historical campaign setups long after the API call finishes.

Yes. You can restrict the agent using the `allowed_tools` parameter. If you only want it searching inventory, you can allow `list_sites` and `list_zones` while blocking access to advertiser data.

The system processes proprietary flight delivery rules, targeting zones, and advertiser IDs. Vinkius operates on a zero-trust architecture, meaning your MCP connection uses ephemeral tokens that never persist. Your ad network internals remain strictly confined to your own vector store and agent runtime.

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