What is airis-mcp-supabase-selfhost CLAUDE.md?

Development instructions for an MCP server, a program that lets coding agents use tools, for self-hosted Supabase databases. It supports database access that follows Row Level Security rules and read-only schema checks.

Use it when working on this repository: install dependencies, run auto-reloading development mode, type-check TypeScript, build the project, or start the server.

It gives contributors the commands and runtime details needed to install, develop, check, build, and start the server.

How agiletec-inc/airis-mcp-supabase-selfhost configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to agiletec-inc/airis-mcp-supabase-selfhost. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/agiletec-inc/airis-mcp-supabase-selfhost/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/agiletec-inc/airis-mcp-supabase-selfhost

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/agiletec-inc/airis-mcp-supabase-selfhost/claude-md/github.svg)](https://agentmods.dev/instructions/agiletec-inc/airis-mcp-supabase-selfhost/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/agiletec-inc/airis-mcp-supabase-selfhost/claude-md"><img src="https://agentmods.dev/badge/instructions/agiletec-inc/airis-mcp-supabase-selfhost/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/agiletec-inc/airis-mcp-supabase-selfhost/claude-md"><img src="https://agentmods.dev/badge/instructions/agiletec-inc/airis-mcp-supabase-selfhost/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,014 This file is loaded in full into every session.

When invoked 2,014 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02014	$0.02014
Opus 5.5	$0.00806	$0.00806
Sonnet 5.5	$0.00403	$0.00403
Haiku 4.5	$0.00201	$0.00201

Measured 2mo ago against content hash dc7b4afe2c76, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

airis-mcp-supabase-selfhost CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:3100/health

CLAUDE.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

This is an MCP (Model Context Protocol) server for self-hosted Supabase deployments. It provides a 2-layer backend architecture:

PostgREST Layer: RLS-aware data access respecting Row Level Security policies
Direct PostgreSQL Layer: Schema introspection and diagnostics (read-only by default)

All tools use the sbsh_ prefix to avoid collision with official Supabase MCP and PostgreSQL MCP servers.

Development Commands

Host-native (default)

Per the org runtime rule (SSoT: ~/.claude/rules/runtime-workflow.md — dev は deploy 先に一致させる、host-native 既定), this MCP server runs host-native on the Mac. Build/dev/test invoke the native Node toolchain (pnpm) directly — do not run the server itself inside Docker.

# Install dependencies
pnpm install

# Development mode (auto-reload via tsx watch)
pnpm dev

# Build TypeScript (tsc)
pnpm build

# Start server (node dist/server.js)
pnpm start

# Type checking (tsc --noEmit)
pnpm typecheck

Server runs on port 3100 by default (configurable via PORT env var).

Docker — connected infra & parity only

Docker is used in two narrow cases, never for running this server during normal dev:

Local stateful infra: the self-hosted Supabase / PostgreSQL stack this server connects to (PostgREST + Postgres) runs in Docker.
Parity verification: optionally run the server in a container to mirror deploy-target behavior before shipping. The Makefile / compose.yaml workspace targets (make up-workspace, make up, make logs, make down, make health, make list-tools) exist for this; they are not the default loop.

Architecture & Code Structure

Single-File Server Design

The entire MCP server is implemented in src/server.ts (~435 lines). This is intentional for simplicity and clarity.

Key components:

Configuration (lines 8-14): Environment variable loading with defaults
- PG_DSN: PostgreSQL connection string
- POSTGREST_URL: PostgREST endpoint
- POSTGREST_JWT: JWT token for PostgREST auth
- READ_ONLY: Safety mode (default: true)
- FEATURES: Feature flags (database, docs, postgrest, functions, storage)
- PORT: HTTP listen port (default: 3100)

Read the full file on GitHub · 229 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 229 lines · 2,014 tokens per session scan A dc7b4afe2c76

Subscribe to this mod's changes

airis-mcp-supabase-selfhost CLAUDE.md is an instructions file published in the GitHub repository agiletec-inc/airis-mcp-supabase-selfhost (0 stars, last pushed 3mo ago), licensed MIT. It adds 2,014 tokens to every session, about $0.0081 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

airis-mcp-supabase-selfhost CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
airis-mcp-supabase-selfhost CLAUDE.mdagiletec-inc/airis-mcp-supabase-selfhost	Instructions file	0	3mo ago	MIT	A	2,014	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

airis-mcp-supabase-selfhost: Instructions file for Claude Code