What is mcp-redshift CLAUDE.md?

A set of project instructions for an MCP server that lets Microsoft Copilot run Amazon Redshift database queries using the user's verified identity. Redshift is Amazon's cloud data warehouse, and MCP is a way for an AI agent to use external tools.

Building, testing, and maintaining the Redshift MCP server while following its Docker, typing, coverage, identity, and SQL rules.

It records the project's required commands, design rules, security checks, testing standards, and code layout in one place.

How RodolfoMCarneiro/mcp-redshift configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to RodolfoMCarneiro/mcp-redshift. 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/RodolfoMCarneiro/mcp-redshift/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/RodolfoMCarneiro/mcp-redshift

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/rodolfomcarneiro/mcp-redshift/claude-md/github.svg)](https://agentmods.dev/instructions/rodolfomcarneiro/mcp-redshift/claude-md)

Your own site

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

Per session 746 This file is loaded in full into every session.

When invoked 746 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.00746	$0.00746
Opus 5	$0.00373	$0.00373
Sonnet 5	$0.00149	$0.00149
Haiku 4.5	$0.00075	$0.00075

Measured 8d ago against content hash 719731bd27e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-redshift CLAUDE.md scanned grade A with 0 findings 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 8d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — MCP Redshift

MCP server (Python 3.13) exposing Amazon Redshift queries to Microsoft Copilot with the user's identity propagated end to end (Entra ID OBO + Redshift native IdP).

Documents that govern the project

docs/implementation-roadmap.md — phases, tasks and status. Tick the checkboxes when tasks finish.
docs/tools-spec.md — tool contracts, envelope, error codes, security invariants. The source of truth for behavior.
docs/adr/ — architecture decisions. New/reversed decision = new ADR.

Non-negotiable rules

Nothing runs on the host. Every command (tests, lint, server, scripts) goes through docker compose / make (ADR-0002). Do not install dependencies or run Python locally.
Every function has complete type hints (parameters and return) and a Google-style docstring in English (see the normative example in ADR-0004). mypy --strict and ruff D rules are gates.
Coverage is a gate: ≥ 90% global, ≥ 95% in auth/, pool.py, params.py and the guardrails.
Identity comes only from the validated token — never from a custom header, tool argument or session state (spec §1.3.1).
SQL only with bind parameters — f-string/format/concatenation with values is forbidden (spec §1.3.3).
Never log tokens/secrets at any level; .env and .token_cache.json are never committed.
New external dependency = port (Protocol) + real adapter + local fake/emulator + contract suite (ADR-0003).

Commands

make is not available on this Windows host — use the compose commands directly:

docker compose up -d postgres dynamodb mock-idp                # start emulators
docker compose run --rm test                                   # full suite with coverage
docker compose run --rm test sh scripts/ci.sh                  # what CI runs (lint+mypy+secrets+tests)
docker compose run --rm test sh -c "ruff format . && ruff check --fix ."   # auto-format
docker compose run --rm test python scripts/seed_dynamodb.py   # seed dynamodb-local

Read the full file on GitHub · 49 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.

8d ago First seen · 49 lines · 746 tokens per session scan A 719731bd27e0

Subscribe to this mod's changes

mcp-redshift CLAUDE.md is an instructions file published in the GitHub repository RodolfoMCarneiro/mcp-redshift (0 stars, last pushed 29d ago), licensed Apache-2.0. It adds 746 tokens to every session, about $0.0037 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Databases

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-redshift: Instructions file for Claude Code