How to Use the Basin MCP in AutoGen

Q: How do I load Basin tools into AutoGen?

Install autogen-extmcp. Use mcpservertools with your endpoint URL, and pass the resulting list directly into your AssistantAgent constructor.

Q: Can AutoGen agents list all my Basin forms?

They can. An agent will call listforms to understand what capture points exist in your account before deciding which specific form IDs to monitor.

Give AutoGen agents control over your form backend. Let them debate lead quality, filter spam, and manage Basin webhooks autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Basin MCP to AutoGen

Create your Vinkius account to connect Basin 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.

GDPR Free for Subscribers

Setup Basin with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Lead Qualification

One agent pulling data is fine. A team of agents debating the value of a lead is better. You connect the Basin MCP Server so your AutoGen squad can pull form entries and argue about their priority. A data-gatherer agent runs `get_latest_submission` to fetch the newest entry. A sales-focused agent evaluates the company name, while a security agent checks the IP address before they agree on next steps.

Consensus-Driven Spam Filtering

False positives kill revenue. Instead of relying on a dumb keyword filter, your agents discuss ambiguous submissions to decide if they are actually junk. If the security agent thinks an entry is a bot, it proposes running `mark_as_spam`. The sales agent reviews the payload and either agrees or vetoes it, ensuring legitimate users never get accidentally deleted by `delete_submission`.

Autonomous Webhook Management

Systems fail. When a downstream CRM drops a connection, your AutoGen setup notices the missing data and initiates a recovery protocol. The operations agent uses `get_form` to check the configuration. Once it confirms the endpoint is back online, it executes `refire_webhooks` to push the stalled payloads through.

Setup guide

Set up Basin 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 includes mcp_server_tools for 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 AssistantAgent and call agent.run(). The agent invokes Basin tools and returns structured results.

agent.py

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="Basin_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Basin data")
print(result.messages[-1].content)

Get your connection token →

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. McpWorkbench is 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=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

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="Basin_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Basin data")
    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 Basin. 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 Basin 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 Basin MCP in AutoGen

Install autogen-ext[mcp]. Use mcp_server_tools with your endpoint URL, and pass the resulting list directly into your AssistantAgent constructor.

They can. An agent will call `list_forms` to understand what capture points exist in your account before deciding which specific form IDs to monitor.

Hardcoding API logic for multiple agents creates a mess. This MCP integration provides a standardized toolset that any agent in your chat room can discover and use safely.

If an agent determines a flagged entry is actually a real customer, it triggers `mark_as_not_spam`. It can then follow up by running `update_submission` to add notes about the false positive.

Form submissions containing emails and phone numbers stay locked down. The server runs in a zero-trust sandbox, meaning your sensitive lead data is only exposed to the specific agents you authorize during the session.

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