Planetscale MCP Server

Created By
PlanetScale4 months ago
The PlanetScale MCP server is a hosted MCP server that exposes your PlanetScale organizations, databases, branches, schema, and Insights data to MCP-compatible tools. It's authenticated via OAuth for configurable access to permissions and scopes, and it's accessible from any MCP client that supports HTTP-hosted servers.
Overview

PlanetScale CLI Build status

PlanetScale is more than a database and our CLI is more than a jumble of commands. The pscale command line tool brings branches, deploy requests, and other PlanetScale concepts to your fingertips.

PlanetScale CLI

Installation

macOS

pscale is available via a Homebrew Tap, and as downloadable binary from the releases page:

brew install planetscale/tap/pscale

Optional: pscale requires a MySQL 8 Client in your PATH for certain commands. You can install it by running:

brew install mysql-client@8.4

To upgrade to the latest version:

brew upgrade pscale

Linux

pscale is available as downloadable binaries from the releases page. Download the .deb or .rpm from the releases page and install with sudo dpkg -i and sudo rpm -i respectively.

Arch: pscale-cli-bin

Windows

pscale is available via scoop, and as a downloadable binary from the releases page:

scoop bucket add pscale https://github.com/planetscale/scoop-bucket.git
scoop install pscale mysql

To upgrade to the latest version:

scoop update pscale

Manually

Download the pre-compiled binaries from the releases page and copy to the desired location.

Alternatively, you can install bin which works on all macOS, Windows, and Linux platforms:

bin install https://github.com/planetscale/cli

To upgrade to the latest version

bin upgrade pscale

Container images

We provide ready to use Docker container images. To pull the latest image:

docker pull planetscale/pscale:latest

To pull a specific version:

docker pull planetscale/pscale:v0.63.0

If you like to have a shell alias that runs the latest version of pscale from docker whenever you type pscale:

mkdir -p $HOME/.config/planetscale
alias pscale="docker run -e HOME=/tmp -v $HOME/.config/planetscale:/tmp/.config/planetscale --user $(id -u):$(id -g) --rm -it -p 3306:3306/tcp planetscale/pscale:latest"

If you need a more advanced example that works with service tokens and differentiates between commands that need a pseudo terminal or non-interactive mode, have a look at this shell function.

MCP Server Integration

Deprecated: The CLI-based MCP server (pscale mcp) is deprecated and will be removed in a future version. Use the PlanetScale MCP server instead: https://planetscale.com/docs/connect/mcp

GitHub Actions Usage

Use the setup-pscale-action to install and use pscale in GitHub Actions.

- name: Setup pscale
  uses: planetscale/setup-pscale-action@v1
- name: Use pscale
  env:
    PLANETSCALE_SERVICE_TOKEN_ID: ${{ secrets.PLANETSCALE_SERVICE_TOKEN_ID }}
    PLANETSCALE_SERVICE_TOKEN: ${{ secrets.PLANETSCALE_SERVICE_TOKEN }}
  run: |
    pscale deploy-request list my-db --org my-org

Local Development

To run a command:

go run cmd/pscale/main.go <command>

Alternatively, you can build pscale:

go build cmd/pscale/main.go

And then use the pscale binary built in cmd/pscale/ for testing:

./cmd/pscale/pscale <command>

Documentation

Please checkout our Documentation page: planetscale.com/docs

Server Config

{
  "mcpServers": {
    "planetscale": {
      "command": "pscale",
      "args": [
        "mcp",
        "server"
      ]
    }
  }
}
Project Info
Created At
4 months ago
Updated At
3 months ago
Author Name
PlanetScale
Star
-
Language
-
License
-
Category
Tags

Recommend Servers

View All
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

5 hours ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago