How to Use the Neon MCP in AutoGen

Q: How do AutoGen agents share Neon project IDs?

One agent runs listprojects and drops the output into the shared chat context. The other agents parse the JSON response to grab the IDs they need.

Q: Can AutoGen promote a Neon branch to primary automatically?

Yes. An agent calls setprimarybranch after a successful debate. This shifts the default compute endpoint to the newly promoted branch.

Q: Do the agents know if a Neon project is running Postgres 15 or 17?

They find out by running getproject. The resulting metadata includes the exact PostgreSQL version and AWS region.

Q: What happens if two agents try to create a branch at the same time?

The MCP protocol handles the requests sequentially. The createbranch tool executes for the first caller, and the second agent receives the updated state.

Let AutoGen agents debate your Neon infrastructure changes. Build consensus-driven systems that provision serverless Postgres environments.

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 AutoGen

Create your Vinkius account to connect Neon 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 Neon with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent consensus for Neon

The `delete_project` tool destroys all branches, databases, and data within a workspace. You configure a security agent to challenge any deletion request. It debates the operational agent, demanding proof that the project is truly obsolete before allowing the execution. The operational agent pulls data using `list_endpoints` to show that all compute nodes have been suspended for weeks. Once both agents agree the resource is dead, they proceed with the deletion.

Coordinate schema tests via MCP Server

The `create_branch` tool generates a copy-on-write clone of your primary database. A developer agent requests a sandbox environment, and an infrastructure agent provisions it. They negotiate the exact naming convention and parent branch ID based on the current project state. Once the sandbox is ready, the infrastructure agent calls `get_connection_uri`. It hands the credentials back to the developer agent, which then runs its migration scripts against the isolated branch.

Provision roles through agent debate

The `create_role` tool generates new database credentials. If an application agent requests full admin access, a DBA agent intercepts the request. It runs `list_roles` to see existing privileges and argues for a more restricted user role instead. They settle on a read-only configuration. The DBA agent calls `create_endpoint` to spin up a read replica, binds the new role to it, and delivers the secure connection string to the application agent.

Setup guide

Set up Neon 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 Neon 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="Neon_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Neon 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="Neon_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Neon 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 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 AutoGen

One agent runs `list_projects` and drops the output into the shared chat context. The other agents parse the JSON response to grab the IDs they need.

Yes. An agent calls `set_primary_branch` after a successful debate. This shifts the default compute endpoint to the newly promoted branch.

They find out by running `get_project`. The resulting metadata includes the exact PostgreSQL version and AWS region.

The MCP protocol handles the requests sequentially. The `create_branch` tool executes for the first caller, and the second agent receives the updated state.

The server handles plain-text passwords and connection URIs from `create_role`. Vinkius isolates this data in an ephemeral, single-use sandbox, ensuring credentials never leak across different agent conversations.

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