Pgsandbox — Data skill for Claude Code
Agent-facing MCP for disposable Postgres experimentation databases.
How to install Pgsandbox
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open LVTD-LLC/pgsandbox and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Pgsandbox does
Agent-facing MCP for disposable Postgres experimentation databases.
Alternatives in Data
- Private GPT — Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more 57.5k ★
- Context Mode — Benchmark Results — Benchmarked against real outputs from popular Claude Code MCP servers, Skills, and dev tools 5.6k ★
- MCP Server Chart — 🤖 A visualization mcp & skills contains 25+ visual charts using @antvis 4k ★
README
PGSandbox
PGSandbox is a local-first Rust CLI and MCP stdio server that lets coding agents create, inspect, use, clone, and delete disposable PostgreSQL databases. It is for engineers who want agents to validate migrations, SQL, seed data, and backend bug reproductions against a real isolated database without touching a shared developer database.
Key Features
- Creates one tracked PostgreSQL database and one scoped login role per task.
- Starts and reuses a managed local Postgres cluster under
~/.pgsandbox/by default, without Docker and without bindinglocalhost:5432. - Supports explicit external Postgres admin profiles when you intentionally opt in through environment variables or a JSON config file.
- Enforces positive TTLs, max TTL caps, metadata-backed deletion, and optional per-owner active sandbox quotas.
- Runs user SQL through sandbox role credentials, not the admin connection.
- Returns bounded, typed SQL result sets so agents do not dump unbounded rows.
- Describes schemas, computes schema digests, diffs schemas, creates named
schema snapshots, and returns
EXPLAIN (FORMAT JSON)plans. - Runs repo migration, seed, and smoke commands with sandbox credentials injected through environment variables or validated app-specific aliases, plus bounded stdin and output controls instead of temporary repo files.
- Returns host-local and Docker-friendly connection variants so containerized local apps can reach a host-managed sandbox without guessing the right host.
- Creates reusable local template artifacts from PGSandbox-owned sandboxes.
- Writes MCP client config for Codex, Cursor, VS Code, and Claude Desktop.
- Masks admin URLs and sandbox credentials in diagnostics and safe summaries.
Table Of Contents
- Tech Stack
- Prerequisites
- Getting Started
- Development From This Repo
- Architecture
- [Environment Variables](#environment-va
Related Skills
Read Only Postgres
by jawwadfirdousi - Read-only PostgreSQL query skill for Claude Code. Executes SELECT/SHOW/EXPLAIN/WITH querie
Yotta Agent Hardening
YuanSafe (元安全) — defensive hardening workflow for AI agents: static config-facing scan of an agent's own runti
Redis MCP Server
A Redis MCP server (pushed to https://github.com/modelcontextprotocol/servers/tree/main/src/redis) implementat
Open Brain
Semantic memory for AI agents. Postgres + pgvector + MCP. Capture, classify, retrieve.
AI Crew Sync
Coordination bus for teams of AI coding agents — Claude Code, Codex, Cursor or any MCP client — sharing messag
HyperMnesia
Self-hosted long-term memory for AI coding agents: Postgres+pgvector doc-RAG (component/constraint map + hybri
Related Agents
Prose Walker
Executes workflow prose exactly as a live session would, against a disposable test world, and returns a transc
Verification Engineer
Independent verification engineer that reproduces reported behavior, executes acceptance, regression, and fail
Data Specialist
Senior data specialist covering exploratory analysis, statistical modeling, machine learning, experimentation,