# Developer Protocol

**Server:** onebusaway-mcp-server
**Version:** 0.1.15
**Package:** [@cyanheads/onebusaway-mcp-server](https://www.npmjs.com/package/@cyanheads/onebusaway-mcp-server)
**Framework:** [@cyanheads/mcp-ts-core](https://www.npmjs.com/package/@cyanheads/mcp-ts-core) `^0.13.6`
**Engines:** Bun ≥1.4.0, Node ≥24.0.0
**MCP SDK:** `@modelcontextprotocol/server` ^2.0.0
**Zod:** ^4.6.5

> **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.

---

## 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

```ts
import { tool, z } from '@cyanheads/mcp-ts-core';
import { JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors';
import { getOneBusAwayService } from '@/services/onebusaway/onebusaway-service.js';

export const getStop = tool('onebusaway_get_stop', {
  title: 'Get Stop Details',
  description: 'Fetch details for a specific stop by ID.',
  annotations: { readOnlyHint: true },
  input: z.object({
    stopId: z.string().min(1).describe('Agency-prefixed stop ID (e.g. "1_75403").'),
  }),
  output: z.object({
    id: z.string().describe('Agency-prefixed stop ID.'),
    name: z.string().describe('Stop name.'),
    routeIds: z.array(z.string()).describe('IDs of routes that serve this stop.'),
  }),
  errors: [
    {
      reason: 'stop_not_found',
      code: JsonRpcErrorCode.NotFound,
      when: 'Stop ID does not exist on this instance.',
      recovery: 'Search for the stop with onebusaway_find_stops or onebusaway_search_stops to get a valid ID.',
    },
  ],

  async handler(input, ctx) {
    const stop = await getOneBusAwayService().getStop(input.stopId, ctx);
    ctx.log.info('getStop completed', { stopId: input.stopId });
    return stop;
  },

  format: (result) => [{
    type: 'text',
    text: `## ${result.name}\n**ID:** ${result.id}\n**Routes:** ${result.routeIds.join(', ')}`,
  }],
});
```

### Resource

```ts
import { resource, z } from '@cyanheads/mcp-ts-core';
import { getOneBusAwayService } from '@/services/onebusaway/onebusaway-service.js';

export const stopResource = resource('onebusaway://stop/{stopId}', {
  name: 'onebusaway-stop',
  description: 'Stop metadata — name, coordinates, served routes, and wheelchair accessibility.',
  mimeType: 'application/json',
  params: z.object({ stopId: z.string().describe('Agency-prefixed stop ID.') }),
  async handler(params, ctx) {
    return getOneBusAwayService().getStop(params.stopId, ctx);
  },
});
```

### Server config

```ts
// src/config/server-config.ts
import { z } from '@cyanheads/mcp-ts-core';
import { parseEnvConfig } from '@cyanheads/mcp-ts-core/config';

const ServerConfigSchema = z.object({
  apiKey: z.string().default('TEST').describe('OneBusAway API key.'),
  baseUrl: z.string().default('https://api.pugetsound.onebusaway.org').describe('Base URL.'),
});

let _config: z.infer<typeof ServerConfigSchema> | undefined;
export function getServerConfig() {
  _config ??= parseEnvConfig(ServerConfigSchema, {
    apiKey: 'ONEBUSAWAY_API_KEY',
    baseUrl: 'ONEBUSAWAY_BASE_URL',
  });
  return _config;
}
```

`parseEnvConfig` maps Zod schema paths → env var names so errors name the variable (`ONEBUSAWAY_API_KEY`) not the path (`apiKey`). Throws `ConfigurationError`, which the framework prints as a clean startup banner.

### Session posture and shutdown

```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). This server declares `stateless` — no tool asks the caller for input mid-handler via `ctx.requestInput`, so there is nothing a stateless connection cannot serve. Add `require: 'stateful'` if that ever changes: 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. Key properties:

| Property | Description |
|:---------|:------------|
| `ctx.log` | Request-scoped logger — `.debug()`, `.info()`, `.notice()`, `.warning()`, `.error()`. Auto-correlates requestId, traceId, tenantId. Dual-sink: Pino and client-visible `notifications/message`. |
| `ctx.state` | Tenant-scoped KV — `.get(key)`, `.set(key, value, { ttl? })`, `.delete(key)`, `.getMany(keys)`, `.list(prefix, { cursor, limit })`. Accepts any serializable value. |
| `ctx.requestInput` | Suspend and ask the caller for more input. Never returns; the handler is re-entered with the answers. |
| `ctx.inputs` | Reader over a retried request's responses. Empty on the first round. |
| `ctx.enrich` | Success-path agent context — notices, query echoes, totals, and truncation disclosure. |
| `ctx.content` | Non-text content blocks for `content[]`; never enters `structuredContent`. |
| `ctx.signal` | `AbortSignal` for cancellation. |
| `ctx.requestId` | Unique request ID. |
| `ctx.tenantId` | Tenant ID from JWT or `'default'` for stdio. |

---

## 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, and the linter enforces conformance against the handler body. `recovery` is required descriptive metadata for the agent's next move (≥ 5 words, lint-validated). Pass `ctx.recoveryFor('reason')` as the throw's data to put it on the wire (`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. Forwarding it is lint-enforced per throw site (`error-contract-recovery-unforwarded`). 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
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}`, ctx.recoveryFor('no_match'));
  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.DatabaseError, '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() entry point — registers tools/resources, inits service
  config/
    server-config.ts                    # ONEBUSAWAY_API_KEY, ONEBUSAWAY_BASE_URL, ONEBUSAWAY_RATE_LIMIT_* (Zod schema)
  services/
    onebusaway/
      onebusaway-service.ts             # OneBusAway service — wraps onebusaway-sdk, paces upstream calls, error classification
      types.ts                          # Domain types (Stop, Route, Arrival, Vehicle, etc.)
  mcp-server/
    tools/definitions/
      list-agencies.tool.ts             # onebusaway_list_agencies
      find-stops.tool.ts                # onebusaway_find_stops
      search-stops.tool.ts              # onebusaway_search_stops
      get-stop.tool.ts                  # onebusaway_get_stop
      find-routes.tool.ts               # onebusaway_find_routes
      search-routes.tool.ts             # onebusaway_search_routes
      get-route.tool.ts                 # onebusaway_get_route
      list-routes-for-agency.tool.ts    # onebusaway_list_routes_for_agency
      get-arrivals.tool.ts              # onebusaway_get_arrivals
      get-trip.tool.ts                  # onebusaway_get_trip
      get-vehicles.tool.ts              # onebusaway_get_vehicles
      get-schedule-for-stop.tool.ts     # onebusaway_get_schedule_for_stop
      get-schedule-for-route.tool.ts    # onebusaway_get_schedule_for_route
    resources/definitions/
      stop.resource.ts                  # onebusaway://stop/{stopId}
      route.resource.ts                 # onebusaway://route/{routeId}
tests/                                  # Vitest tests covering all tools and resources
```

---

## Naming

| What | Convention | Example |
|:-----|:-----------|:--------|
| Files | kebab-case with suffix | `search-docs.tool.ts` |
| Tool/resource/prompt names | snake_case | `search_docs` |
| Directories | kebab-case | `src/services/doc-search/` |
| Descriptions | Single string or template literal, no `+` concatenation | `'Search items by query and filter.'` |

---

## 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-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 |
| `techniques` | Catalog of reusable response/data-shaping patterns — e.g. outline-on-overflow for oversized document payloads |
| `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 |
| `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 |
| `api-auth` | Auth modes, scopes, JWT/OAuth |
| `api-linter` | Definition linter rule catalog — invoked by `bun run lint:mcp` and `devcheck` |
| `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, request input, enrichment, content, logger, and state |
| `api-errors` | McpError, JsonRpcErrorCode, error patterns |
| `api-mirror` | MirrorService: persistent, self-refreshing local mirror of a bulk upstream dataset via embedded SQLite + FTS5 — 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 |
| `orchestrations` | Chain task skills into a gated multi-phase pipeline — build-out, QA-fix, update-ship — when you can spawn sub-agents |

**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 <cmd>` is the standard invocation. `npm run <cmd>` also works (npm delegates to Bun).

| Command | Purpose |
|:--------|:--------|
| `bun run build` | Compile TypeScript |
| `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 <name>`, then `bun dedupe` |
| `bun run audit:refresh` | Delete `bun.lock` and reinstall. Last resort after `audit:fix`, `bun update <name>`, and `bun dedupe` — re-resolves every ranged dep (the framework pin included) and rewrites the lockfile as `lockfileVersion: 2` |
| `bun run lint:mcp` | Validate MCP definitions against the framework rule catalog |
| `bun run lint:packaging` | Validate packaging and plugin metadata surfaces |
| `bun run list-skills` | Print the skill registry |
| `bun run tree` | Generate directory structure doc |
| `bun run format` | Auto-fix formatting |
| `bun run format:unsafe` | Also apply Biome's unsafe fixes; review the diff |
| `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 release:github` | Create GitHub Release from the current annotated tag |
| `bun run bundle` | Build, pack, and clean a `.mcpb` for one-click Claude Desktop install |

**CI is one file.** `.github/workflows/codeql.yml` 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

`bun 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. 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/<major.minor>.x/<version>.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 `bun 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 `bun 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
agent-notes: ""                           # optional — downstream maintenance instructions
---

# 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 release PR, straight-through** — `git-wrapup`'s "Release PR mode", mode `straight-through`. One run: `git-wrapup` lands the commit stack on `release/<version>`, pushes it, and opens the PR (title = the release commit subject, body = the changelog entry plus a gates section); `release-and-publish` then 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. A caller's brief may run a given release as `gated` instead — a `release-pr-review` pass on the open PR before `release-and-publish`. **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.

---

## 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 { getMyService } from '@/services/my-domain/my-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.<option>}"` — mirror the `user_config` block in `manifest.json`. Never write `"KEY": ""` into `env`
- [ ] `bun run devcheck` passes