Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Compares an OpenAPI YAML/JSON spec to a list of implemented routes and flags drift: missing operations, extra routes, method mismatches, and path-parameter shape differences. Use when reviewing API PRs, before a release, or asking "does our code still match the OpenAPI?". Includes a stdlib Python checker with --self-test.
Simulates API rate limits before you ship them - token bucket, fixed window, sliding log and sliding counter, per client, endpoint, tier or global - against generated or recorded traffic with retrying clients. Shows who gets 429s and for how long, fixed-window boundary bursts, retry herds, noisy neighbours, abusive clients that still get through and peaks over backend capacity. Includes an offline stdlib Python simulator with --self-test.
Reviews PostgreSQL and MySQL schema migrations (raw SQL or ORM-generated) for table locks, rewrites, data loss, and breaking changes, then proposes safe zero-downtime rewrites with a clear verdict.
Plans safe API call budgets across services and environments: maps quotas and burst limits, sizes caches and queues, and spots which jobs will trip 429s before they hit production.
Finds code nobody uses anymore: unused files, exports, routes, styles and dependencies, with proof for each one, and suggests small safe pull requests to remove them.
Plans a major framework upgrade step by step, such as React, Next.js, Django or Rails: reads the breaking changes, maps what in your code they hit, and splits the work into small safe pull requests.
Ships server-side issues as small, reviewed PRs. Made for the Lean Software Factory team.