How to Use the Neon MCP in LangChain

Q: How do I pass Neon connection strings between LangChain tools?

Your agent calls getconnectionuri and pipes the output into the next chain. The URI acts as a standard string input for downstream database loaders.

Q: Can LangChain agents delete my primary Neon branch?

No. The deletebranch tool blocks deletion of the primary branch. Your agent has to call setprimarybranch on a different target first.

Q: Does LangSmith track the exact PostgreSQL version I provisioned?

Yes. When your agent runs createproject, the inputs like the AWS region and Postgres version show up in your trace logs.

Build multi-step database provisioning pipelines with LangChain. Turn serverless Postgres operations into traceable agent actions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Neon MCP to LangChain

Create your Vinkius account to connect Neon 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 Neon with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain database branches in LangChain

The `create_project` tool spins up a new serverless Postgres environment with a default branch and read-write endpoint. Your ReAct agent grabs the resulting project ID and passes it directly to `create_branch` to isolate schema changes. You get instant, copy-on-write database clones without writing manual provisioning scripts. LangChain passes the output of these operations down the pipeline. If a test fails, your agent catches the error and executes `delete_branch` to clean up the workspace automatically. Every step logs latency and token usage in LangSmith.

Automate credentials via MCP Server

The `create_role` tool generates new database users and passwords on the fly. Your agent checks existing permissions using `list_roles`, decides if a new service account is needed, and provisions it within the specified branch. Instead of hardcoding credentials, the agent calls `get_connection_uri` to fetch the exact connection string for the new role. It then feeds that URI into the next link in your chain, like a vector store loader or an ORM validation step.

Route compute endpoints dynamically

The `create_endpoint` tool lets your agent provision read-only or read-write compute nodes for specific branches. When your chain detects heavy read volume, it spins up a read replica and fetches its host address. You monitor the active, idle, or suspended states using `list_endpoints`. The agent reads the current autoscaling configuration and decides whether to route traffic to the primary branch or a temporary compute instance.

Setup guide

Set up Neon 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 Neon 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({
    "neon-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 Neon 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 Neon. 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 Neon 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 Neon MCP in LangChain

Your agent calls `get_connection_uri` and pipes the output into the next chain. The URI acts as a standard string input for downstream database loaders.

No. The `delete_branch` tool blocks deletion of the primary branch. Your agent has to call `set_primary_branch` on a different target first.

The LangChain execution halts and raises the error. You build fallback logic to catch this and run `list_branches` to check the current environment state.

Yes. When your agent runs `create_project`, the inputs like the AWS region and Postgres version show up in your trace logs.

The server processes raw connection URIs and generated passwords from `create_role`. Vinkius runs the integration inside an ephemeral V8 Isolate Sandbox, meaning your database credentials vanish from memory the moment the execution ends.

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