How to Use the Neon MCP in CrewAI

Q: How do I add the Neon MCP tools to a CrewAI agent?

Pass your Vinkius HTTP URL directly into the mcps array when defining your Agent. CrewAI automatically discovers the Neon commands and equips the agent to use them.

Q: Can multiple CrewAI agents share the Neon MCP Server?

Yes. You can expose the entire server to a crew, or use MCPServerHTTP with a toolfilter to give specific agents access to specific commands, like isolating createrole to a security agent.

Q: How does a CrewAI agent know which Neon branch to modify?

Agents maintain shared session memory. If Agent A runs listbranches and finds a stale environment, Agent B remembers that specific branch ID when executing deletebranch.

Deploy autonomous database administration crews. Let specialized CrewAI agents provision, monitor, and manage your Neon Postgres infrastructure.

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 CrewAI

Create your Vinkius account to connect Neon to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy Neon MCP Server Crews

`create_project` and `create_branch` allow your autonomous database administrators to spin up serverless Postgres environments on demand. You assign these tools to an Infrastructure Agent inside CrewAI. When a developer submits a ticket for a new staging environment, the agent reads the request, clones the primary branch, and reports back. The real power comes from agent collaboration. A separate Security Agent takes the new branch ID and runs `create_role` to generate isolated credentials. Because CrewAI agents share memory, the Security Agent knows exactly what the Infrastructure Agent just built. They work sequentially to deliver a fully configured, secure database without human input.

Autonomous Infrastructure Auditing

`list_projects`, `list_branches`, and `list_endpoints` feed real-time usage data into your monitoring crews via the MCP protocol. You set up a regular task where an Auditor Agent scans your entire Neon organization. It checks for idle endpoints or branches that haven't been touched in weeks. Based on that analysis, the crew takes action. The Auditor Agent passes a list of stale branch IDs to a Cleanup Agent. Using `delete_branch`, the Cleanup Agent prunes the dead environments, keeping your Neon resource limits under control. You build a self-maintaining infrastructure loop.

Dynamic Endpoint Management

`create_endpoint` and `set_primary_branch` give your agents control over compute resources and routing. If a specific branch needs heavier read capacity, a Performance Agent can provision a new read-only endpoint automatically. The agent specifies the exact branch ID and endpoint type, adapting your infrastructure to current demands. You filter exactly what each agent can do. Using CrewAI's `tool_filter`, you restrict the Auditor Agent to read-only commands like `list_databases`, while only the Lead DBA Agent gets access to `delete_project`. This hierarchical execution ensures specialized agents stay strictly within their defined operational lanes.

Setup guide

Set up Neon MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Neon tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Neon Analyst",
    goal="Access and analyze Neon data via MCP.",
    backstory="Expert analyst with direct Neon access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Neon transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Neon Analyst",
        goal="Access and analyze Neon data via MCP.",
        backstory="Expert analyst with direct Neon access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Neon transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass your Vinkius HTTP URL directly into the `mcps` array when defining your Agent. CrewAI automatically discovers the Neon commands and equips the agent to use them.

Yes. You can expose the entire server to a crew, or use `MCPServerHTTP` with a `tool_filter` to give specific agents access to specific commands, like isolating `create_role` to a security agent.

Agents maintain shared session memory. If Agent A runs `list_branches` and finds a stale environment, Agent B remembers that specific branch ID when executing `delete_branch`.

The tools return synchronous metadata from the Neon API. The agent receives the active state immediately from `create_endpoint` and proceeds to the next task in the sequence.

This integration touches raw PostgreSQL connection strings and role credentials through `get_connection_uri`. Vinkius routes these requests through an ephemeral sandbox that requires only a single endpoint token, guaranteeing your core database secrets are never exposed to external logging systems.

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