# Developer Protocol **Server:** ourairports-mcp-server **Version:** 0.2.6 **Framework:** [@cyanheads/mcp-ts-core](https://www.npmjs.com/package/@cyanheads/mcp-ts-core) `^0.13.15` **Engines:** Bun ≥1.4.0, Node ≥24.0.0 **MCP SDK:** `@modelcontextprotocol/server` ^2.3.1 **Zod:** ^4.6.7 > **Read the framework docs first:** `node_modules/@cyanheads/mcp-ts-core/CLAUDE.md` contains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only. --- ## What This Server Does Static, offline aviation reference data from the public-domain [OurAirports](https://ourairports.com/) dataset — airports, runways, navaids, radio frequencies. The six source CSVs are bundled into the package (and baked into the Docker image at build time via `scripts/build-data.ts`); the `airport-data` service parses them into in-memory indices once at `setup()`, and every tool is a local query. Zero runtime API: no key, no rate limit, no upstream to retry. The surface is six read-only tools plus the `airport://{code}` resource; no prompts. The architecture rationale (why in-memory indices over MirrorService/DataCanvas, the five-space code resolution, the haversine geo scan) lives in `docs/design.md` — read it before changing the service or adding a tool. --- ## What's Next? When the user asks what's next or needs direction, suggest options based on the current project state. Common next steps: 1. **Re-run the `setup` skill** — ensures CLAUDE.md, skills, structure, and metadata are populated and up to date with the current codebase 2. **Run the `design-mcp-server` skill** — if the tool/resource surface hasn't been mapped yet, work through domain design 3. **Add tools/resources/prompts** — scaffold new definitions using the `add-tool`, `add-app-tool`, `add-resource`, `add-prompt` skills 4. **Add services** — scaffold domain service integrations using the `add-service` skill 5. **Add tests** — scaffold tests for existing definitions using the `add-test` skill 6. **Field-test definitions** — exercise tools/resources/prompts with real inputs using the `field-test` skill, get a report of issues and pain points 7. **Run `devcheck`** — lint, format, typecheck, and security audit 8. **Run the `security-pass` skill** — audit handlers for MCP-specific security gaps: output injection, scope blast radius, input sinks, tenant isolation 9. **Run the `polish-docs-meta` skill** — finalize README, CHANGELOG, metadata, and agent protocol for shipping 10. **Run the `maintenance` skill** — investigate changelogs, adopt upstream changes, and sync skills after `bun update --latest` Tailor suggestions to what's actually missing or stale — don't recite the full list every time. --- ## Core Rules - **Logic throws, framework catches.** Tool/resource handlers are pure — throw on failure, no `try/catch`. Plain `Error` is fine; the framework catches, classifies, and formats. Use error factories (`notFound()`, `validationError()`, etc.) when the error code matters. - **Use `ctx.log`** for request-scoped logging. No `console` calls. - **Use `ctx.state`** for tenant-scoped storage. Never access persistence directly. - **Need input the caller didn't supply?** `return ctx.requestInput(...)` and read `ctx.inputs` when the handler is re-entered. Never `await` for user input mid-handler. - **Secrets in env vars only** — never hardcoded. - **Cut noise.** Add only what earns its place: no speculative generality, no guards for states the framework already prevents (Zod-validated params, classified errors), no abstraction until a third caller proves it, no option nothing sets. - **Close the loop on issues.** When implementing work tracked by a GitHub issue, comment on the issue with what landed and close it. Do both — a comment without a close leaves stale issues open; a close without a comment leaves no record of what shipped. The comment is for future readers — state the concrete changes, not the conversation that produced them. --- ## Patterns ### Tool Real example — `ourairports_get_airport`. Handlers are synchronous here (every query hits the in-memory index, no `await`), pull the service via its accessor, throw a typed contract error on no match, and `format()` renders every output field for content/structuredContent parity. ```ts import { tool, z } from '@cyanheads/mcp-ts-core'; import { JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors'; import { getAirportDataService } from '@/services/airport-data/airport-data-service.js'; export const getAirportTool = tool('ourairports_get_airport', { title: 'Get Airport', description: 'Fetch the full record for one airport resolved by ANY code …', annotations: { readOnlyHint: true, idempotentHint: true, openWorldHint: false }, errors: [ { reason: 'unknown_code', code: JsonRpcErrorCode.NotFound, when: 'No airport matched the supplied code in any identifier space.', recovery: 'Try ourairports_search_airports with a partial name or municipality.', }, ], input: z.object({ code: z.string().min(1).describe('Any airport code: IATA/ICAO/GPS/local/ident. Case-insensitive.'), }), output: z.object({ /* AirportSummarySchema + resolvedVia + runways + frequencies */ }), handler(input, ctx) { const svc = getAirportDataService(); const resolution = svc.resolveByCode(input.code); if (!resolution) { throw ctx.fail('unknown_code', `No airport found for code "${input.code}".`, { code: input.code, }); } // … hydrate runways/frequencies, enrich country/region names … }, format: (result) => [{ type: 'text', text: /* every output field rendered */ '' }], }); ``` Shared output schemas and domain→output mappers live in `src/mcp-server/tools/definitions/_schemas.ts` so `get_airport`, the `airport://` resource, and the search/find tools render the same fields the same way. `format()` parity is lint-enforced — every field in `output` must appear in the rendered text. ### Resource The `airport://{code}` resource is a stable-URI twin of `ourairports_get_airport`, delegating to the same service accessor. No `list()` — discovery is `ourairports_search_airports`. ```ts import { resource, z } from '@cyanheads/mcp-ts-core'; import { getAirportDataService } from '@/services/airport-data/airport-data-service.js'; export const airportResource = resource('airport://{code}', { name: 'airport-record', title: 'Airport Record', description: 'A single airport record by any code (IATA/ICAO/GPS/local/ident) …', mimeType: 'application/json', params: z.object({ code: z.string().min(1).describe('Any airport code. Case-insensitive.') }), output: z.object({ /* same shape as ourairports_get_airport */ }), handler(params, ctx) { const resolution = getAirportDataService().resolveByCode(params.code); if (!resolution) throw ctx.fail('unknown_code', `No airport found for code "${params.code}".`); // … same hydration as the tool … }, }); ``` ### Prompts None. This is a data/lookup server with no recurring multi-step interaction pattern worth templating. `createApp()` is called with `prompts: []`. ### Server config The real schema — two optional knobs, no API key. `OURAIRPORTS_DATA_DIR` defaults to the bundled `data/` (resolved by `resolveBundledDataDir()` when unset). `parseEnvConfig` treats empty values and unsubstituted MCPB placeholders as unset. ```ts // src/config/server-config.ts — lazy-parsed, separate from framework config import { z } from '@cyanheads/mcp-ts-core'; import { parseEnvConfig } from '@cyanheads/mcp-ts-core/config'; const ServerConfigSchema = z.object({ dataDir: z .string().optional() .describe('Directory holding the six OurAirports CSV files. Defaults to the bundled `data/`.'), defaultSearchLimit: z.coerce .number().int().min(1).max(100).default(20) .describe('Default result cap for search/find tools when the caller omits `limit`.'), }); let _config: z.infer | undefined; export function getServerConfig() { _config ??= parseEnvConfig(ServerConfigSchema, { dataDir: 'OURAIRPORTS_DATA_DIR', defaultSearchLimit: 'OURAIRPORTS_DEFAULT_SEARCH_LIMIT', }); return _config; } ``` `parseEnvConfig` maps Zod schema paths → env var names so errors name the variable (`OURAIRPORTS_DATA_DIR`) not the path (`dataDir`). Throws `ConfigurationError`, which the framework prints as a clean startup banner. For env booleans use `z.stringbool()`, never `z.coerce.boolean()` — `Boolean("false")` is `true`, so a coerced flag can't be disabled through the environment. ### Server identity and instructions `createApp()` sets the bare repo name on display surfaces and the default HTTP session posture in source. The package description is read from `package.json`: ```ts await createApp({ name: 'ourairports-mcp-server', title: 'ourairports-mcp-server', sessionMode: 'stateless', instructions: 'Resolve airport codes with ourairports_get_airport and search by name with ourairports_search_airports.', }); ``` `instructions` is optional server-level orientation, sent on every `initialize` as session-level context. Use it for deployment guidance (connection aliases, regional notes, scope hints) instead of repeating the same context across tool descriptions. Client adoption is uneven, but there's no downside when set. ### Session posture and shutdown Two more `createApp()` options shape how the server runs rather than how it presents itself: ```ts await createApp({ sessionMode: 'stateless', // or { default: 'stateful', require: 'stateful' } setup(core) { startMyWatcher(core.config); }, async teardown() { await stopMyWatcher(); }, }); ``` `sessionMode` declares the HTTP session posture in `src/` instead of leaving it to a deployment's `MCP_SESSION_MODE`, which still wins whenever it carries a meaningful value (an empty string and an unsubstituted `${…}` placeholder read as unset and fall through to the option). Add `require: 'stateful'` when a tool asks the caller for input mid-handler via `ctx.requestInput`: startup then fails with a `ConfigurationError` rather than serving a mode in which a 2025-era client can never answer the prompt. Stdio is never refused. `teardown(core)` is the `setup()` counterpart — release a watcher, socket, or non-`unref()`'d timer there. It runs after the transport stops and before the logger closes, on every shutdown path, and a signal-triggered shutdown then exits the process explicitly (0, or 1 if a step never settles within the framework's 10 s ceiling). --- ## Context Handlers receive a unified `ctx` object. This server is read-only over an in-memory index — it uses the logging, enrichment, and error sub-APIs and nothing stateful. The properties actually used here: | Property | Description | |:---------|:------------| | `ctx.log` | Request-scoped logger — `.debug()`, `.info()`, `.notice()`, `.warning()`, `.error()`. Auto-correlates requestId, traceId, tenantId. Dual-sink: Pino **and** `notifications/message` to the client, so treat it as client-visible. | | `ctx.enrich` | Success-path agent context (empty-result notices, query echo, pagination totals) — `ctx.enrich(...)` or `.notice()` / `.total()` / `.echo()` / `.truncated()`. Reaches `structuredContent` and `content[]`; lands only when the definition declares an `enrichment` block (no-op otherwise). Used by the search/find/list tools to disclose match counts, truncation, and empty-result guidance. | | `ctx.fail` | Throw a typed contract error — `ctx.fail(reason, message?, data?)`, typed against the tool's `errors[]` reason union. | The framework also exposes `ctx.state` (tenant KV; accepts any JSON-serializable value, and reads return its JSON form — a `Date` comes back as an ISO string), `ctx.requestInput` / `ctx.inputs` (multi-round-trip input), `ctx.content` (success-path content), and `ctx.signal` — unused here (no persistence, no user prompts, no extra content blocks, no upstream I/O to cancel). See the framework CLAUDE.md / `api-context` skill for the full interface. --- ## Errors Handlers throw — the framework catches, classifies, and formats. **Recommended: typed error contract.** Declare `errors: [{ reason, code, when, recovery, retryable?, severity?, thrownBy? }]` on `tool()` / `resource()` to receive `ctx.fail(reason, …)` typed against the reason union. TypeScript catches typos at compile time, `data.reason` is auto-populated for observability, linter enforces conformance against the handler body. `recovery` is required (≥ 5 words, lint-validated) — the single source of truth for the agent's next move. The framework puts it on the wire whenever a failure carrying that `reason` arrives without a hint — a bare `ctx.fail('reason')` or a service throw with `data: { reason }` — as `data.recovery.hint`, mirrored into `content[]` text unless the message already contains it verbatim; override with an explicit `{ recovery: { hint: '...' } }` when dynamic runtime context matters. Every error envelope also carries `data.requestId`, the id the server's log records for that call carry, and `content[]` closes with `(reason … · request )`. Mark an entry the service layer throws with `thrownBy: 'service'` so `error-contract-unthrown` skips it — lint-only metadata, nothing at runtime reads it. Baseline codes (`InternalError`, `ServiceUnavailable`, `Timeout`, `ValidationError`, `SerializationError`, `RequestCancelled`) bubble freely and don't need declaring. ```ts import { JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors'; errors: [ { reason: 'no_match', code: JsonRpcErrorCode.NotFound, when: 'No item matched the query', recovery: 'Broaden the query or check the spelling and try again.' }, ], async handler(input, ctx) { const item = await db.find(input.id); if (!item) throw ctx.fail('no_match', `No item ${input.id}`); return item; } ``` **Declare contracts inline on each tool.** The contract is part of the tool's public surface — one file should give the full picture. Don't extract a shared `errors[]` constant; per-tool repetition is the intended cost of locality. **Fallback (no contract entry fits):** throw via factories or plain `Error`. ```ts // Error factories — explicit code import { notFound, serviceUnavailable } from '@cyanheads/mcp-ts-core/errors'; throw notFound('Item not found', { itemId }); throw serviceUnavailable('API unavailable', { url }, { cause: err }); // Plain Error — framework auto-classifies from message patterns throw new Error('Item not found'); // → NotFound throw new Error('Invalid query format'); // → ValidationError // McpError — when no factory exists for the code import { McpError, JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors'; throw new McpError(JsonRpcErrorCode.InitializationFailed, 'Connection failed', { pool: 'primary' }); ``` See framework CLAUDE.md and the `api-errors` skill for the full auto-classification table, all available factories, and the contract reference. --- ## Structure ```text src/ index.ts # createApp() — registers tools/resources, loads index at setup() config/ server-config.ts # OURAIRPORTS_DATA_DIR + OURAIRPORTS_DEFAULT_SEARCH_LIMIT (Zod) services/ airport-data/ airport-data-service.ts # Load-on-setup() index, code resolution, search, geo accessors csv.ts # Header-keyed CSV parser data-dir.ts # Resolves the bundled data/ directory (override-aware) geo.ts # Haversine distance + bearing types.ts # Airport/Runway/Navaid/Frequency domain types + enums mcp-server/ tools/definitions/ _schemas.ts # Shared output schemas + domain→output mappers + renderers search-airports.tool.ts # ourairports_search_airports search-runways.tool.ts # ourairports_search_runways get-airport.tool.ts # ourairports_get_airport find-airports.tool.ts # ourairports_find_airports find-navaids.tool.ts # ourairports_find_navaids list-countries.tool.ts # ourairports_list_countries index.ts # allToolDefinitions barrel resources/definitions/ airport.resource.ts # airport://{code} index.ts # allResourceDefinitions barrel scripts/ build-data.ts # Build-time fetch + bundle of the six OurAirports CSVs into data/ data/ # Bundled CSVs (gitignored locally; baked into the package + image) docs/design.md # Architecture rationale — read before changing the service ``` --- ## Naming | What | Convention | Example | |:-----|:-----------|:--------| | Files | kebab-case with suffix | `get-airport.tool.ts` | | Tool names | snake_case, `ourairports_` prefix (matches the repo/display name) | `ourairports_get_airport` | | Directories | kebab-case | `src/services/airport-data/` | | Descriptions | Single string or template literal, no `+` concatenation | `'Fetch the full record for one airport resolved by ANY code …'` | --- ## Skills Skills are modular instructions in `framework-skills/` at the project root. Read them directly when a task matches — e.g., `framework-skills/add-tool/SKILL.md` when adding a tool. `bun run list-skills` prints the full registry. The directory is deliberately not `skills/`: Claude Code and Codex auto-load a plugin's root `skills/`, so a server that ships `.claude-plugin/` or `.codex-plugin/` would hand these development skills to every agent that installs it. Keep `skills/` free for skills meant for those agents. **Agent skill directory:** Copy skills into the directory your agent discovers (Claude Code: `.claude/skills/`, others: equivalent). Skills then load as context without referencing `framework-skills/` paths. After framework updates, run the `maintenance` skill — Phase B re-syncs the agent directory. Available skills: | Skill | Purpose | |:------|:--------| | `setup` | Post-init project orientation | | `design-mcp-server` | Design tool surface, resources, and services for a new server | | `add-tool` | Scaffold a new tool definition | | `add-app-tool` | Scaffold an MCP App tool + paired UI resource | | `add-resource` | Scaffold a new resource definition | | `add-prompt` | Scaffold a new prompt definition | | `add-service` | Scaffold a new service integration | | `add-provider` | Scaffold a service provider implementation | | `add-export` | Add a framework export surface | | `add-test` | Scaffold test file for a tool, resource, or service | | `field-test` | Exercise tools/resources/prompts with real inputs, verify behavior, report issues | | `tool-defs-analysis` | Read-only audit of MCP definition language across the surface — voice, leaks, defaults, recovery hints, output descriptions | | `security-pass` | Audit server for MCP-flavored security gaps: output injection, scope blast radius, input sinks, tenant isolation | | `code-simplifier` | Post-session cleanup against `git diff` — modernize syntax, consolidate duplication, align with the codebase | | `polish-docs-meta` | Finalize docs, README, metadata, and agent protocol for shipping | | `git-wrapup` | Land working-tree changes as a commit stack — version bump, changelog, verify, commit by concern, release commit on top. No tag, no push to main; opens the release PR when the project declares release PR mode | | `release-pr-review` | Review pass on an open release PR — simplifier + correctness review, fixes as ordinary commits on top of the stack, PR body kept in sync. Release PR mode only | | `release-and-publish` | Fast-forward merge (release PR mode) + tag + push + npm + MCP Registry + GH Release + Docker. Picks up from `git-wrapup` | | `maintenance` | Investigate changelogs, adopt upstream changes, sync skills to agent dirs | | `orchestrations` | Chain task skills into a gated multi-phase pipeline — build-out, QA-fix, update-ship — when you can spawn sub-agents | | `report-issue-framework` | File a bug or feature request against `@cyanheads/mcp-ts-core` via `gh` CLI | | `report-issue-local` | File a bug or feature request against this server's own repo via `gh` CLI | | `techniques` | Catalog of response/data-shaping techniques — overflow handling, payload shaping, retrieval patterns | | `api-auth` | Auth modes, scopes, JWT/OAuth | | `api-canvas` | DataCanvas: register tabular data, run SQL, export, plus the `spillover()` helper for big result sets — Tier 3 opt-in | | `api-config` | AppConfig, parseConfig, env vars | | `api-context` | Context interface, RequestContext, logger, state, multi-round-trip input | | `api-errors` | McpError, JsonRpcErrorCode, error patterns | | `api-linter` | Definition linter rule catalog — invoked by `bun run lint:mcp` and `devcheck` | | `api-mirror` | MirrorService: persistent self-refreshing local mirror (embedded SQLite + FTS5) of a bulk upstream dataset — Tier 3 opt-in | | `api-services` | LLM, Speech, Graph services | | `api-testing` | createMockContext, test patterns | | `api-utils` | Formatting, parsing, security, pagination, scheduling, telemetry helpers | | `api-telemetry` | OTel catalog: spans, metrics, completion logs, env config, cardinality rules | | `api-workers` | Cloudflare Workers runtime | **Chaining skills into pipelines.** When the user wants a multi-phase effort — build this server out, QA-and-fix the surface, update-and-ship — *and you can spawn sub-agents*, `framework-skills/orchestrations/SKILL.md` sequences the task skills above into a gated pipeline with verification at each step. Read it to drive the run. Optional: skip it if you can't orchestrate sub-agents, and ignore it entirely if you were *spawned* as one — you've already been scoped to a single phase. When you complete a skill's checklist, check the boxes and add a completion timestamp at the end (e.g., `Completed: 2026-03-11`). --- ## Commands **Runtime:** Scripts use Bun's native TypeScript execution — `bun run ` is the standard invocation. `npm run ` also works (npm delegates to bun). | Command | Purpose | |:--------|:--------| | `bun run build` | Compile TypeScript | | `bun run build:data` | Fetch the six OurAirports CSVs from the daily GitHub mirror and bundle them into `data/`. Run before `build` and in the Docker build stage; `--check` verifies already-bundled files without downloading. | | `bun run rebuild` | Clean + build | | `bun run clean` | Remove build artifacts | | `bun run devcheck` | Lint + format + typecheck + security + changelog sync | | `bun run audit:fix` | `bun audit fix` — upgrade vulnerable packages to the lowest safe version within existing ranges (`--dry-run` previews, `--latest` rewrites ranges). First response when `devcheck` flags a transitive advisory; then `bun update `, then `bun dedupe` | | `bun run audit:refresh` | Delete `bun.lock` and reinstall. Last resort after `audit:fix`, `bun update `, and `bun dedupe` — re-resolves every ranged dep (the framework pin included) and rewrites the lockfile as `lockfileVersion: 2` | | `bun run lint:mcp` | Run the MCP definition linter standalone (rule catalog: `api-linter` skill) | | `bun run lint:packaging` | Packaging surface checks — `server.json`/`manifest.json` env-var parity (run by devcheck) | | `bun run list-skills` | Print the skill registry | | `bun run tree` | Generate directory structure doc | | `bun run format` | Auto-fix formatting (safe fixes only) | | `bun run format:unsafe` | Also apply Biome's unsafe autofixes — review the diff; they can change behavior | | `bun run test` | Run tests (Vitest — use `bun run test`, not `bun test`) | | `bun run start:stdio` | Production mode (stdio) | | `bun run start:http` | Production mode (HTTP) | | `bun run changelog:build` | Regenerate `CHANGELOG.md` from `changelog/*.md` | | `bun run changelog:check` | Verify `CHANGELOG.md` is in sync (used by devcheck) | | `bun run bundle` | Build, pack, and clean a `.mcpb` for one-click Claude Desktop install | **CI is one file.** `.github/workflows/codeql.yml` (scaffolded) is the only GitHub Actions workflow: CodeQL is GitHub-owned end to end, and the file runs only while the repo's CodeQL *default setup* is turned off. Verification — `devcheck`, tests, the release gates — runs locally; don't add a workflow that re-runs it. --- ## Bundling `npm run bundle` produces a `.mcpb` extension bundle for one-click install in Claude Desktop. The pack step is followed by `scripts/clean-mcpb.ts`, which prunes dev dependencies (`mcpb clean`) and strips two classes of `node_modules/**` content that root-anchored `.mcpbignore` patterns cannot reach: dependency-shipped agent docs (`framework-skills/`, `skills/`, `.claude/`, `.agents/`, `SKILL.md`) and platform-specific native bindings, which would otherwise lock the bundle to the platform it was packed on. A server using DataCanvas therefore ships a portable bundle without the DuckDB native — `@duckdb/node-api` is an optional peer loaded lazily, so canvas tools report an actionable install hint and every other tool works normally. MCPB is stdio-only — HTTP and Cloudflare Workers deployments are unaffected. Consumers who don't need it can delete `manifest.json` and `.mcpbignore`; `lint:packaging` skips cleanly. **Adding an env var requires both files:** `server.json` (registry discovery, `environmentVariables[]`) and `manifest.json` (bundle install UX, `mcp_config.env` + `user_config`). `lint:packaging` (run by `devcheck`) verifies the env var names match, that every `user_config` option is wired into `mcp_config.env` as `"X": "${user_config.X}"` (the host substitutes nothing else — `"${X}"` reaches the server as that literal string), and that an optional string option carries `"default": ""`. **README install badges** (Claude Desktop `.mcpb`, Cursor, VS Code) and the `base64` / `encodeURIComponent` config-generation commands are ship-time concerns — run the `polish-docs-meta` skill, which carries the badge format, layout, and generation snippets in `framework-skills/polish-docs-meta/references/readme.md`. --- ## Changelog Directory-based, grouped by minor series via the `.x` semver-wildcard convention. Source of truth: `changelog/.x/.md` (e.g. `changelog/0.1.x/0.1.0.md`) — one file per release, shipped in the npm package. At release, author the per-version file with a concrete version and date, then run `npm run changelog:build` to regenerate the rollup. `changelog/template.md` is a **pristine format reference** — never edited or moved; read it for the frontmatter + section layout when scaffolding. `CHANGELOG.md` is a **navigation index** (header + link + summary per version), regenerated by `npm run changelog:build` — devcheck hard-fails on drift; never hand-edit it. Each per-version file opens with YAML frontmatter: ```markdown --- summary: "One-line headline, ≤350 chars" # required — powers the rollup index breaking: false # optional — true flags breaking changes security: false # optional — true ONLY for a source-code security fix, never a dependency CVE bump --- # 0.1.0 — YYYY-MM-DD ... ``` `breaking: true` renders a `· ⚠️ Breaking` badge — use it when consumers must update code on upgrade (signature changes, removed APIs, config renames). `security: true` renders a `· 🛡️ Security` badge and pairs with a `## Security` body section — set it only for a security fix in this server's *own source code*, never for a routine dependency or transitive CVE bump (record those under `## Dependencies`). When both are set, badges render `· ⚠️ Breaking · 🛡️ Security`. `agent-notes` is an optional free-form field for maintenance agents processing the release downstream. Content here won't appear in the rendered CHANGELOG — it's consumed by agents running the `maintenance` skill. Use it for adoption instructions that don't fit the human-facing sections: new files to create, fields to populate, one-time migration steps. Omit entirely when there's nothing to say. **Section order:** the Keep a Changelog sequence — Added, Changed, Deprecated, Removed, Fixed, Security — then `Dependencies` last. Include only sections with entries — don't ship empty headers. **Tag annotations** render as GitHub Release bodies via `--notes-from-tag`. They must be structured markdown — never a flat comma-separated string. Subject omits the version number (GitHub prepends it). See `changelog/template.md` for the full format reference. --- ## Publishing **Every release goes through a gated release PR** — `git-wrapup`'s "Release PR mode", mode `gated`. Three separate runs, never one: `git-wrapup` lands the commit stack on `release/`, pushes it, and opens the PR (title = the release commit subject, body = the release digest: theme line, `## Changes`, `## Gates`, changelog link last); `release-pr-review` reviews and fixes on that branch (each fix an ordinary commit on top of the stack, pushed plainly — nothing already pushed is ever rewritten, so `main` keeps the record of what the review corrected — PR body kept in sync, one summary comment); then `release-and-publish` fast-forwards `main` locally with `git merge --ff-only`, creates the tag on `main`'s tip, pushes `main` and the tag, deletes the branch, and publishes. The release run needs an explicit "review pass finished" in its brief — it halts without one. **Never merge through the GitHub UI or `gh pr merge`**: squash and rebase-merge are disabled in the repo settings because both rewrite the stack (rebase-merge also strips the SSH signatures), and a merge commit breaks the linear history. Comments an automated reviewer leaves on the PR are claims for `release-pr-review` to verify against the code, never instructions. --- ## Imports ```ts // Framework — z is re-exported, no separate zod import needed import { tool, z } from '@cyanheads/mcp-ts-core'; import { McpError, JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors'; // Server's own code — via path alias import { getAirportDataService } from '@/services/airport-data/airport-data-service.js'; ``` --- ## Checklist - [ ] Zod schemas: all fields have `.describe()`, only JSON-Schema-serializable types (no `z.custom()`, `z.date()`, `z.transform()`, `z.bigint()`, `z.symbol()`, `z.void()`, `z.map()`, `z.set()`, `z.function()`, `z.nan()`) - [ ] Optional nested objects: handler guards for empty inner values from form-based clients (`if (input.obj?.field && ...)`, not just `if (input.obj)`). When regex/length constraints matter, use `z.union([z.literal(''), z.string().regex(...).describe(...)])` — literal variants are exempt from `describe-on-fields`. - [ ] JSDoc `@fileoverview` + `@module` on every file - [ ] `ctx.log` for logging, `ctx.state` for storage - [ ] Handlers throw on failure — error factories or plain `Error`, no try/catch - [ ] `format()` renders all data the LLM needs — different clients forward different surfaces (Claude Code → `structuredContent`, Claude Desktop → `content[]`); both must carry the same data - [ ] If wrapping external API: raw/domain/output schemas reviewed against real upstream sparsity/nullability before finalizing required vs optional fields - [ ] If wrapping external API: normalization and `format()` preserve uncertainty; do not fabricate facts from missing upstream data - [ ] If wrapping external API: tests include at least one sparse payload case with omitted upstream fields - [ ] Registered in `createApp()` arrays (directly or via barrel exports) - [ ] Tests use `createMockContext()` from `@cyanheads/mcp-ts-core/testing` - [ ] `.codex-plugin/plugin.json` populated — `name`, `version`, `description`, `repository`, `license` from `package.json`; `interface.displayName` = the unscoped repo name (never the npm scope — `lint:packaging` enforces this); `interface.shortDescription` from `package.json` description - [ ] `.codex-plugin/mcp.json` updated — server name key is the unscoped repo name; every user-supplied variable (API key, contact email, instance URL) is listed in `env_vars` so Codex forwards it from the user's environment. Never write `"KEY": ""` into `env` — an empty value replaces the user's exported key and is read as unset - [ ] `.claude-plugin/plugin.json` populated — `name`, `version`, `description`, `author`, `repository`, `license`, `keywords` from `package.json`; inline `mcpServers` entry keyed by the unscoped repo name. Every user-supplied variable is declared under `userConfig` (`type`, `title`, `description`; `sensitive: true` for keys and tokens; `required: true` or `default: ""`) and referenced from `env` as `"KEY": "${user_config.