How to Use the Basis Technologies MCP in LangChain

Q: How do I connect the Basis Technologies MCP Server to LangChain?

Install langchain-mcp-adapters and langgraph. You initialize the connection using MultiServerMCPClient pointing to your Vinkius endpoint, then pass the tools directly into your ReAct agent.

Q: Can LangChain agents automatically check Basis Technologies campaign performance?

They handle it natively. The agent decides when to call getcampaignperformance based on your prompt. You just ask for a weekly summary, and it manages the sequential lookups.

Q: Does LangSmith trace the MCP tool calls?

Every single one. You see the exact inputs sent to gettactic and the raw JSON response returned by the tools. Debugging latency takes seconds instead of hours.

Build ReAct agents that pull Basis Technologies DSP metrics directly into LangChain workflows.

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 LangChain

Create your Vinkius account to connect Basis Technologies to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Basis DSP metrics into automated LangChain reports

You start your LangChain workflows by identifying active campaigns with `list_campaigns`. Once the agent grabs those IDs, it immediately feeds them into `get_campaign_performance` to pull the spend and conversion data. You give the system an objective, and it figures out the path. The output of one tool becomes the input for the next. Your script takes the raw performance metrics, passes them through a formatting prompt, and drops a finished daily wrap-up into Slack. LangSmith tracks every token and MCP Server call along the way.

Build custom logic around tactic performance

Stop manually checking line items by wiring `list_clients` and `list_brands` into a ReAct agent. Once it identifies the target accounts, it pulls active line items via `list_tactics`. You dictate the threshold, and the agent executes the loop. The agent evaluates the return on ad spend by calling `get_tactic_performance`. If a placement underperforms, the chain triggers an alert or logs the specific tactic ID for review. This MCP Server integration turns static dashboards into automated watchdogs.

Inspect ad creatives with LangGraph pipelines

Complex marketing audits require structured execution, starting with `list_ads` to grab the entire catalog. LangGraph lets you build cyclical graphs that audit every piece of creative across an account. You get a fully automated compliance checker running in the background. From there, individual nodes in your graph run `get_ad` to pull the exact specs, dimensions, and approval statuses. No human intervention needed. You just review the final report generated by the chain.

Setup guide

Set up Basis Technologies MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Basis Technologies tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "basis-technologies-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Basis Technologies transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install `langchain-mcp-adapters` and `langgraph`. You initialize the connection using `MultiServerMCPClient` pointing to your Vinkius endpoint, then pass the tools directly into your ReAct agent.

They handle it natively. The agent decides when to call `get_campaign_performance` based on your prompt. You just ask for a weekly summary, and it manages the sequential lookups.

Every single one. You see the exact inputs sent to `get_tactic` and the raw JSON response returned by the tools. Debugging latency takes seconds instead of hours.

The agent catches the error and tries again. You write the fallback logic in your chain to either skip the missing creative or ask the user for clarification before proceeding.

Vinkius routes your requests through an isolated V8 sandbox. When your agent pulls ad spend or tactic metrics, that data stays in memory just long enough to generate the response. The ephemeral environment destroys itself immediately after execution, leaving zero trace of your advertiser IDs.

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