What is mcp-https-OAuth-database-template CLAUDE.md?

Repository instructions for a Python Model Context Protocol server with OAuth 2.1 and PKCE authentication. OAuth and PKCE are web sign-in methods that let clients connect securely without sharing a password directly.

Use them when developing or operating this MCP server, including local stdio mode, HTTP or SSE connections, HTTPS deployment, formatting, type checking, and linting.

They explain how to install dependencies, run the server locally or over HTTPS, and check code quality.

mcp-https-OAuth-database-template CLAUDE.md — Instructions file by achimstruve

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/achimstruve/mcp-https-oauth-database-template/claude-md

Clone the repo

git clone --depth 1 https://github.com/achimstruve/mcp-https-OAuth-database-template

Per session 1,559 This file is loaded in full into every session.

When invoked 1,559 The same file — it is already loaded in full.

Security scan B 2 findings. Scan, not verified.

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	$0.01559	$0.01559
Opus 5	$0.00779	$0.00779
Sonnet 5	$0.00312	$0.00312
Haiku 4.5	$0.00156	$0.00156

Measured 3d ago against content hash 0be138ff6045, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

mcp-https-OAuth-database-template CLAUDE.md scanned grade B with 2 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 3d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo -E ./scripts/run-with-letsencrypt.sh

Makes network callslowCapability

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

curl http://localhost:8899/sse

CLAUDE.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 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.

Project Overview

This is a production-ready Python MCP (Model Context Protocol) server with OAuth 2.1 + PKCE authentication, designed for web deployment using HTTPS and Server-Sent Events (SSE). It uses the FastMCP framework and provides comprehensive OAuth endpoints for secure client integration.

Development Commands

Setup and Dependencies

# Install project dependencies
uv sync

# Install dev dependencies
uv sync --all-extras

Running the Server

Local development (Claude Desktop - stdio):

# Run in local mode with stdio transport (no OAuth, no HTTPS)
LOCAL_MODE=true uv run python server.py

# This mode is for Claude Desktop integration

Local development (Claude Code - HTTP):

# Run in HTTP mode locally for web clients
uv run python server.py

# Access at http://localhost:8899/sse

Production (HTTPS):

# Run with SSL enabled
SSL_ENABLED=true uv run python server.py

# Access at https://localhost:8443/sse

Code Quality Commands

# Format code
uv run black server.py oauth.py

# Type checking
uv run mypy server.py oauth.py

# Linting
uv run flake8 server.py oauth.py

# Run tests
uv run pytest

Architecture

Main components:

server.py: Main application with HTTPS/SSE web server and comprehensive OAuth endpoints
- Tools: add(a, b) and secret_word()
- Resources: greeting://{name} dynamic resource
- OAuth endpoints: /.well-known/oauth-authorization-server, /.well-known/oauth-protected-resource, /register, /authorize, /callback, /token
- SSE transport for real-time communication with Claude Code
- OAuth-aware authentication wrapper
oauth.py: OAuth 2.1 + PKCE implementation with Google authentication
- Dynamic Client Registration (RFC 7591)
- OAuth Authorization Server Metadata (RFC 8414)
- OAuth Protected Resource Metadata (RFC 8707)
- PKCE support (RFC 7636)
- JWT token generation and validation

Read the full file on GitHub · 213 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.

3d ago First seen · 213 lines · 1,559 tokens per session scan B 0be138ff6045

Subscribe to this mod's changes

mcp-https-OAuth-database-template CLAUDE.md is an instructions file published in the GitHub repository achimstruve/mcp-https-OAuth-database-template (4 stars, last pushed 1y ago), licensed MIT. It adds 1,559 tokens to every session, about $0.0078 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Security

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-https-OAuth-database-template CLAUDE.md