An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect PlanetScale to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run MySQL infrastructure directly from your IDE or agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through PlanetScale.

  1. 01

    Create database

    This capability provisions a new, empty serverless MySQL instance. It sets up the environment so you can immediately run DDL definitions via Deploy Requests.

  2. 02

    Get branch

    This capability retrieves the specific access hostnames for a single database branch. Use it to get the connection details needed for your application code.

  3. 03

    Get database

    This capability pulls the core configuration details for a specific MySQL cluster. It's how your agent inspects the logic and settings of an existing database.

  4. 04

    List branches

    This capability returns a list of all development branches for a database. It's useful for seeing which schema versions are currently active.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through PlanetScale.

  1. 05

    Delete branch

    This capability permanently removes a specific schema branch. It's the fastest way to clean up temporary testing environments after a deployment.

  2. 06

    Delete database

    This capability destroys a PlanetScale MySQL construct entirely. Use it with caution, as it wipes the associated data across the global network.

  3. 07

    List databases

    This capability retrieves a list of all high-availability MySQL distributions in your account. It maps out your existing database clusters.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through PlanetScale.

  1. 08

    Create branch

    This capability forks a new, isolated branch from an existing parent. It clones the schema without duplicating the actual data, making it perfect for safe testing.

  2. 09

    List organizations

    This capability identifies the root organizational IDs in your account. Your agent needs this information to target the correct management endpoints.

  3. 10

    List regions

    This capability shows the physical cloud provider edge locations available. Use it to pick the best region for reducing latency.

Real work

What teams actually run

01

Safe Schema Testing

Fork a production schema into a new branch to test migrations before they go live.

02

Automated Cleanup

Tell your agent to delete all branches that don't match a specific naming pattern.

03

Rapid Prototyping

Instantly provision a new database instance to support a new microservice.

04

Latency Optimization

Check which physical regions are available to place your new database closer to users.

Automate a task

Put PlanetScale to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

PlanetScale works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put PlanetScale to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

960ms average. Fast in production.

PlanetScale is checked daily against the live service.

Daily averagePeak 1185ms
Oct 12Today
Fastest day
692ms
Slowest day
1185ms
14-day trend
Slowing+71%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of PlanetScale, so you can see the experience inside your AI.

It does not authenticate your account with PlanetScale. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

PlanetScale Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_Cj1wlp2M7NG4xG8y4bWLeF2TWX2ttuftARXCdWYR/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — PlanetScale capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "planetscale-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_Cj1wlp2M7NG4xG8y4bWLeF2TWX2ttuftARXCdWYR/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up PlanetScale in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work PlanetScale owners hand off.

This MCP is built for engineers who want to manage database lifecycles through natural language or terminal-based AI workflows.

  • 01

    DevOps Engineers

    They use the agent to automate the removal of stale staging environments via chat.

  • 02

    Full-stack Developers

    They spin up ephemeral database branches for feature work without leaving their IDE.

  • 03

    Platform Architects

    They use the agent to audit node metadata and connection strings across different organizations.

FAQ

Questions PlanetScale owners ask.

  • 01

    Does creating a branch copy all my data?

    No. Creating a branch via this MCP clones the schema only. It does not duplicate the actual data rows, which keeps the process fast and safe.

  • 02

    Can I use this with Cursor or VS Code?

    Yes. This MCP works with any MCP-compatible client, including Cursor, VS Code, Claude, and Windsurf.

  • 03

    How do I manage my PlanetScale credentials?

    Vinkius manages your credentials securely. You only need to provide your PlanetScale Service Token once during setup.

  • 04

    What happens if I delete a database?

    Deleting a database is an irreversible action. It will wipe the associated data across the global network.

  • 05

    Is this compatible with Vitess?

    Yes. This MCP is designed specifically to manage PlanetScale's Vitess-backed MySQL infrastructure.

  • 06

    Can I run destructive commands like deleting databases through this AI implementation?

    Yes. The integration provides delete_branch and delete_database. They map directly to infrastructure teardowns. You should scope the Service Token carefully inside the PlanetScale dashboard to avoid catastrophic misinterpretations if your explicit intent is just testing. Deletions via delete_database are absolute and irretrievable.

  • 07

    Does create_branch replicate and copy my production dataset into the new branch?

    No. PlanetScale branches solely duplicate the static underlying DDL structure (schema), exactly like taking a snapshot of empty tables. The new branch boots up free of rows. This design lets your agent freely run ALTER TABLE operations independently without crashing the master tables.

  • 08

    How does the agent know which organizational node I am provisioning my branches on?

    All queries essentially require the foundational string parameters known as the org_name. If unknown, a simple list_organizations query reveals the UUID scope dictating your authorized account parameter bounds securely.

Explore

More in Loved By Devs

Suggestions

Connect PlanetScale to Claude, Cursor, ChatGPT & more