How to Use the Basin MCP in LangChain

Q: Can my LangChain pipeline update Basin submission metadata?

Yes. The agent can execute updatesubmission based on intermediate chain results. This lets you tag or categorize leads dynamically as they flow through your system.

Q: What happens when LangChain deletes a Basin form submission?

The deletesubmission tool wipes the record permanently from the backend. Make sure your agent logic includes confirmation steps before executing destructive actions.

Wire form backend automation directly into LangChain agents. Read submissions, filter spam, and trigger webhooks inside any ReAct pipeline.

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 LangChain

Create your Vinkius account to connect Basin 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 Basin with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Basin MCP Server Meets LangChain

Your ReAct agent needs live form data to make decisions. Connecting the Basin MCP Server drops real-time submission access right into your LangSmith-traced pipelines. The agent grabs the data it needs and passes it down the chain. You start by calling `list_forms` to map out available capture points. From there, the chain can use `get_latest_submission` to pull fresh leads and pipe them straight into a database or CRM node.

Automated Spam Filtering

Nobody wants junk leads cluttering their database. You build a reasoning step where an LLM evaluates incoming form data for bot-like patterns before anything gets saved. When the agent spots garbage, it fires `mark_as_spam` to clean up the backend. If a legitimate user gets caught in the filter, another node can run `mark_as_not_spam` to fix the mistake immediately.

Webhook Recovery Pipelines

Sometimes external endpoints fail and drop your lead data. Instead of manually clicking buttons in a dashboard, this MCP integration lets your LangChain setup handle the retry logic automatically. The agent detects a missing record in your CRM, pulls the original data with `get_submission`, and runs `refire_webhooks`. It pushes the payload through again without you lifting a finger.

Setup guide

Set up Basin 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 Basin 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({
    "basin-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 Basin 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 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 LangChain

Install the langchain-mcp-adapters package. Use MultiServerMCPClient pointing to the Basin endpoint, then pass the returned tools to your create_agent setup.

Yes. The agent can execute `update_submission` based on intermediate chain results. This lets you tag or categorize leads dynamically as they flow through your system.

Writing custom API wrappers wastes time. This server gives your agent twelve native tools out of the box, with full observability in LangSmith for every request.

The `delete_submission` tool wipes the record permanently from the backend. Make sure your agent logic includes confirmation steps before executing destructive actions.

Your form payloads and lead details stay secure. The MCP connection relies on a single endpoint token, meaning your raw user data only travels between the isolated Vinkius sandbox and your trusted client environment.

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