How to Use the Basis Technologies MCP in LlamaIndex

Q: How do I initialize the Basis Technologies MCP Server in LlamaIndex?

Grab the llama-index-tools-mcp package via pip. Set up a BasicMCPClient with your Vinkius URL, wrap it in McpToolSpec, and pass the async tool list to your agent.

Q: Can I restrict which tools my RAG application uses?

Yes. The allowedtools filter lets you expose specific endpoints. You might give a read-only dashboard access to listcampaigns while hiding the detailed performance metrics.

Index your Basis Technologies campaigns into LlamaIndex for semantic DSP search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Basis Technologies MCP to LlamaIndex

Create your Vinkius account to connect Basis Technologies 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 Basis Technologies with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Basis ad performance into a LlamaIndex RAG index

You convert active campaign metrics from `list_campaigns` into vector embeddings with LlamaIndex. Instead of just reading data, you build a searchable history of your DSP activity. Connect the MCP Server and pull the full metadata for every active push. You then feed those campaign IDs into `get_campaign_performance` and index the results. Now your team can ask natural language questions about past ad spend. The engine retrieves the exact historical context without hallucinating numbers.

Ground your queries in real tactic data

Marketing teams stop digging through dashboards when you build a unified knowledge base using `list_tactics`. The `McpToolSpec` wrapper makes these endpoints available to your FunctionAgent. You pull the data once and query it forever. When someone asks why Q3 conversions dropped, the agent queries the indexed tactic data via `get_tactic_performance` and points directly to the underperforming placements. Hard facts become instantly accessible to anyone in the company.

Cross-reference brand assets and ad creatives

Managing multiple advertisers gets messy fast unless you index every client with `list_clients`. You can build an internal tool that maps out every brand using `list_brands` to establish a clear hierarchy. Once the structure is set, the agent uses `list_ads` and `get_ad` to pull the creative details. Your indexing pipeline maps which ad belongs to which brand. Anyone can search the vector store to find approved creatives instantly.

Setup guide

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

Grab the `llama-index-tools-mcp` package via pip. Set up a `BasicMCPClient` with your Vinkius URL, wrap it in `McpToolSpec`, and pass the async tool list to your agent.

It depends entirely on what you index. You write a script that pulls metrics via `get_campaign_performance` and stores them in your vector database. After that, semantic search works perfectly.

No. The LlamaIndex integration translates the tool definitions automatically. Your agent understands exactly what arguments `get_tactic` requires without any manual mapping.

Yes. The `allowed_tools` filter lets you expose specific endpoints. You might give a read-only dashboard access to `list_campaigns` while hiding the detailed performance metrics.

We handle it strictly. Your client lists and campaign performance metrics pass through a zero-trust Vinkius tunnel. We authenticate the connection with a single endpoint token, and nothing gets stored on our end. You control the vector database where the actual ad data lives.

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