How to Use the Basis Technologies MCP in AutoGen
Let AutoGen agents debate and optimize your Basis Technologies DSP tactics.
Works with every AI agent you already use
…and any MCP-compatible client
Connect Basis Technologies MCP to AutoGen
Create your Vinkius account to connect Basis Technologies to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.
Multi-agent debate on campaign performance via AutoGen
Microsoft's AutoGen framework lets you pull live metrics via `get_campaign_performance` to fuel agent debates. You create a data analyst agent and a media buyer agent. The analyst pulls live numbers using the MCP Server. The media buyer reviews the stats and suggests pausing a line item. The analyst pushes back, pointing out that `get_tactic_performance` shows a delayed conversion window. They negotiate the best move. You get a consensus-driven recommendation instead of a blind guess.
Audit ad creatives through competing perspectives
Compliance and performance rarely agree, so you assign `list_ads` to specialized agents to audit your creatives. One focuses entirely on brand safety, pulling creative specs via `get_ad` to check dimensions and text. The second agent looks at the historical success of those ads. They debate whether a high-performing but edgy creative should stay live across the accounts found in `list_brands`. You watch the logic unfold in the terminal before approving the final call.
Map client hierarchies automatically
Onboarding a massive agency account requires understanding their structure, which an agent does using `list_clients`. It finds the root advertisers and independently maps the entire setup. It passes those IDs to another agent that runs `list_campaigns` for each client. The system builds a complete map of the DSP environment. You just provide the initial prompt and let the agents handle the recursive API calls.
Set up Basis Technologies MCP in AutoGen
Prerequisites
- Python 3.10+ installed
-
autogen-ext[mcp]package - Active Vinkius subscription with a valid endpoint token
- 1
Install AutoGen with MCP
Run
pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includesmcp_server_toolsfor stateless tool access. - 2
Fetch tools from the MCP
Call
mcp_server_tools(SseServerParams(url=...))with your Vinkius endpoint. Replace[YOUR_TOKEN_HERE]with your token from cloud.vinkius.com. - 3
Run your agent
Pass the tools to
AssistantAgentand callagent.run(). The agent invokes Basis Technologies tools and returns structured results.
from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
server_params = SseServerParams(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
tools = await mcp_server_tools(server_params)
agent = AssistantAgent(
name="Basis Technologies_assistant",
model_client=OpenAIChatCompletionClient(model="gpt-4o"),
tools=tools,
)
result = await agent.run("List recent Basis Technologies data")
print(result.messages[-1].content) Prerequisites
- Python 3.10+ installed
-
autogen-ext[mcp]+autogen-agentchat - Active Vinkius subscription with a valid endpoint token
- 1
Install dependencies
Same packages as above.
McpWorkbenchis ideal when your agent needs stateful sessions across multiple tool calls. - 2
Use McpWorkbench as context manager
Wrap your agent in
async with McpWorkbench(...)to maintain shared state and resources. The workbench manages the full MCP session lifecycle. - 3
Run with workbench
Pass
workbench=workbenchto your agent. State is preserved across multiple tool calls within the same session.
from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
server_params = SseServerParams(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
async with McpWorkbench(server_params) as workbench:
agent = AssistantAgent(
name="Basis Technologies_assistant",
model_client=OpenAIChatCompletionClient(model="gpt-4o"),
workbench=workbench,
)
result = await agent.run("List recent Basis Technologies data")
print(result.messages[-1].content) 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.
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 AutoGen
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the Basis Technologies MCP today
We host it, we monitor it, we maintain it. You just paste one token.