mcpField
P
PlanetScale

PlanetScale

Remote
planetscale.comDatabases5Updated 2w ago

About PlanetScale

This repository contains TypeScript tools maintained for the PlanetScale MCP server, shared helper code, and resources for local development and validation. It is one part of the hosted service; some tools are generated from the PlanetScale API OpenAPI specification.

Key features

  1. 01Maintain TypeScript MCP tools
  2. 02Provide shared helper code
  3. 03Support local development and validation
  4. 04Test interactively with Inspector

Use cases

  1. 01Develop and validate repository MCP tools
  2. 02Run the server locally over stdio
  3. 03Inspect tool behavior with MCP Inspector

MCP support

The repository provides some tools for the PlanetScale MCP server; the full hosted service also includes tools generated from the PlanetScale API OpenAPI specification. Developers can run a local stdio MCP server and test it with MCP Inspector.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.pscale.dev/mcp/planetscale
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

PlanetScale MCP Server Tools

This repository contains tool implementations that are part of the PlanetScale MCP server.

The full hosted MCP server includes additional tools that are generated from the PlanetScale API OpenAPI spec, not every production tool lives in this repository.

Related docs

Project scope

This repo is focused on:

  • MCP tools we maintain directly in TypeScript
  • shared helper code used by those tools
  • local development and validation of the open-source portions

Some MCP functionality is intentionally not duplicated here because it is generated from the API spec and maintained in that generation pipeline.

Quick start

Install dependencies:

pnpm install

Build a deployment zip:

pnpm build

Push to Gram:

pnpm push

Testing locally

Run a local MCP server over stdio with inspector support:

pnpm dev

This launches MCP Inspector so you can interactively test tool behavior during development.

Contributing

See CONTRIBUTING.md for contribution workflow and project conventions.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.