@thenavidm/slipway 0.1.11 → 0.1.12

package/CHANGELOG.md

@@ -2,6 +2,10 @@
 
 What changed in Slipway, newest first.
 
+## 0.1.12, 2026-10-05: what the Meta Ad Library needed
+
+- **The write switches appear only where they act.** `<PREFIX>_READ_ONLY` and `<PREFIX>_AUDIT_LOG` are listed in the general help, `agent-context` and the generated settings table only when a tool writes, and `<PREFIX>_ALLOW_DESTRUCTIVE` and `<PREFIX>_CONFIRM` only when a tool can be irreversible, spends money or needs confirming. The Meta Ad Library server only reads, and its help offered to "refuse the irreversible writes"; it is now 40 tokens shorter, 399 against 439. The switches still work if set.
+
 ## 0.1.11, 2026-10-05: what WordPress needed
 
 - **Records no longer advertise `propertyNames`.** Zod 4 gives every `z.record` `propertyNames: { type: "string" }`, which every JSON object key already is, and the Zod 3 converters never wrote it. Slipway leaves it out of what clients receive, as it does the safe-integer bounds, and validation still runs on the schema itself. Each one cost 8 tokens; WordPress has nine. An argument that happens to be named `propertyNames` is a name, so it stays.

package/README.md

@@ -577,12 +577,14 @@ See [CHANGELOG.md](CHANGELOG.md).
 | [Google Photos](https://github.com/thenavidm/google-photos-mcp-cli) | [`@thenavidm/google-photos-mcp-cli`](https://www.npmjs.com/package/@thenavidm/google-photos-mcp-cli) 2.0.0 | The photo picker, uploads, albums and their captions, places and maps, and media this server uploaded, across several Google accounts |
 | [Mastodon](https://github.com/thenavidm/mastodon-mcp-cli) | [`@thenavidm/mastodon-mcp-cli`](https://www.npmjs.com/package/@thenavidm/mastodon-mcp-cli) 2.0.0 | Posting, editing, threads, timelines, search, lists, notifications and following, on any instance |
 | [Midjourney](https://github.com/thenavidm/midjourney-mcp-cli) | [`@thenavidm/midjourney-mcp-cli`](https://www.npmjs.com/package/@thenavidm/midjourney-mcp-cli) 2.0.0 | Generating images and video, following jobs, downloads, moodboards, the account's library and the explore feeds, through a signed-in browser |
+| [Podcast Index](https://github.com/thenavidm/podcastindex-mcp-cli) | [`@thenavidm/podcastindex-mcp-cli`](https://www.npmjs.com/package/@thenavidm/podcastindex-mcp-cli) 2.0.0 | The open podcast directory, with the transcripts and chapters it links to fetched and read, guest histories, feed health and value-for-value |
 | [Substack](https://github.com/thenavidm/substack-mcp-cli) | [`@thenavidm/substack-mcp-cli`](https://www.npmjs.com/package/@thenavidm/substack-mcp-cli) 3.0.0 | Drafts, publishing and scheduling, Notes, subscribers, analytics, tags, comments and researching other publications |
 | [Teachable](https://github.com/thenavidm/teachable-mcp-cli) | [`@thenavidm/teachable-mcp-cli`](https://www.npmjs.com/package/@thenavidm/teachable-mcp-cli) 3.0.0 | Courses, users, enrollments, pricing, coupons and transactions |
 | [Threads](https://github.com/thenavidm/threads-mcp-cli) | [`@thenavidm/threads-mcp-cli`](https://www.npmjs.com/package/@thenavidm/threads-mcp-cli) 2.0.0 | Posting, threads, carousels, replies and reply approvals, insights and keyword search |
 | [TikTok](https://github.com/thenavidm/tiktok-mcp-cli) | [`@thenavidm/tiktok-mcp-cli`](https://www.npmjs.com/package/@thenavidm/tiktok-mcp-cli) 2.0.0 | Your own account's profile and videos, ranked by any metric, posting and drafts, through TikTok's official API |
 | [ThriveCart](https://github.com/thenavidm/thrivecart-mcp-cli) | [`@thenavidm/thrivecart-mcp-cli`](https://www.npmjs.com/package/@thenavidm/thrivecart-mcp-cli) 3.0.0 | Products and pricing, transactions and revenue, customers, subscriptions and affiliates, across several carts |
-| [YouTube](https://github.com/thenavidm/youtube-mcp-cli) | [`@thenavidm/youtube-mcp-cli`](https://www.npmjs.com/package/@thenavidm/youtube-mcp-cli) 3.0.0 | Transcripts of any public video, channel research against each channel's own median, and your own channels' videos, comments and analytics |
+| [WordPress](https://github.com/thenavidm/wordpress-mcp-cli) | [`@thenavidm/wordpress-mcp-cli`](https://www.npmjs.com/package/@thenavidm/wordpress-mcp-cli) 2.0.0 | Posts, pages, custom post types, media, terms, users and comments across several sites, plus Elementor, Rank Math, redirects and bulk edits through a helper plugin |
+| [YouTube](https://github.com/thenavidm/youtube-mcp-cli) | [`@thenavidm/youtube-mcp-cli`](https://www.npmjs.com/package/@thenavidm/youtube-mcp-cli) 3.0.1 | Transcripts of any public video, channel research against each channel's own median, and your own channels' videos, comments and analytics |
 
 Each server was measured against its previous release before it moved: startup, what a client receives, CLI exit codes, and tokens in Claude Code and Codex. Its README has the numbers.
 

package/dist/cli/context.js

@@ -7,7 +7,7 @@
  */
 import { createRequire } from "node:module";
 import { EXIT } from "../errors.js";
-import { policyEnvNames } from "../policy.js";
+import { policyEnvNames, switchesThatApply } from "../policy.js";
 import { outputJsonSchema } from "../schema.js";
 import { exampleCommand, GLOBAL_FLAGS } from "./help.js";
 import { flagsFor } from "./flags.js";
@@ -26,6 +26,7 @@ export const EXIT_MEANINGS = {
 export function agentContext(app, env, bin, options = {}) {
     const policy = app.policy(env);
     const names = policyEnvNames(app.envPrefix);
+    const applies = switchesThatApply(app.allTools);
     const tools = app.tools(env);
     const hidden = app.allTools.length - tools.length;
     // Terminal commands the app adds beside its tools, such as logout, and a sign-in flow that says what it takes.
@@ -78,15 +79,19 @@ export function agentContext(app, env, bin, options = {}) {
                 ...(setting.secret ? { secret: true } : {}),
                 description: setting.description,
             })),
-            { env: names.readOnly, value: policy.readOnly, description: "hide and refuse every write" },
-            { env: names.allowDestructive, value: policy.allowDestructive, description: app.allTools.some((tool) => tool.spends) ? "allow public or irreversible writes and paid calls" : "allow public or irreversible writes" },
+            ...(applies.readOnly ? [{ env: names.readOnly, value: policy.readOnly, description: "hide and refuse every write" }] : []),
+            ...(applies.allowDestructive
+                ? [{ env: names.allowDestructive, value: policy.allowDestructive, description: app.allTools.some((tool) => tool.spends) ? "allow public or irreversible writes and paid calls" : "allow public or irreversible writes" }]
+                : []),
             ...(app.allTools.some((tool) => tool.tags.length > 0)
                 ? [{ env: names.toolsets, value: policy.toolsets === "all" ? "all" : [...policy.toolsets], description: "toolsets that are on" }]
                 : []),
             { env: names.surface, value: policy.surface, description: "full tool list, or search for very large catalogs" },
-            { env: names.auditLog, value: policy.auditLog ?? null, description: "file that records every attempted write" },
+            ...(applies.auditLog ? [{ env: names.auditLog, value: policy.auditLog ?? null, description: "file that records every attempted write" }] : []),
             { env: names.toolTimeoutMs, value: policy.toolTimeoutMs ?? null, description: "deadline for any tool" },
-            { env: names.confirm, value: policy.confirm, description: "who confirms a confirmed call over MCP: human asks a person where the client can, model accepts confirm: true" },
+            ...(applies.confirm
+                ? [{ env: names.confirm, value: policy.confirm, description: "who confirms a confirmed call over MCP: human asks a person where the client can, model accepts confirm: true" }]
+                : []),
             { env: `${app.envPrefix}_HTTP_PORT`, value: env[`${app.envPrefix}_HTTP_PORT`] ?? null, description: `port for --http, ${app.definition.httpPort ?? 8787} when unset` },
             { env: `${app.envPrefix}_HTTP_HOST`, value: env[`${app.envPrefix}_HTTP_HOST`] ?? null, description: "address for --http, 127.0.0.1 when unset; any other needs a token" },
             { env: `${app.envPrefix}_HTTP_TOKEN`, set: Boolean(env[`${app.envPrefix}_HTTP_TOKEN`]), secret: true, description: "bearer token --http requires" },

package/dist/cli/help.js

@@ -5,7 +5,7 @@
  * shows what applies and points to the rest instead of repeating it.
  */
 import { EXIT } from "../errors.js";
-import { policyEnvNames, riskMark, visibility } from "../policy.js";
+import { policyEnvNames, riskMark, switchesThatApply, visibility } from "../policy.js";
 import { firstSentence } from "../search.js";
 import { flagsFor } from "./flags.js";
 const COLUMN = 30;
@@ -205,6 +205,7 @@ function table(rows) {
 }
 export function renderGeneralHelp(app, bin) {
     const names = policyEnvNames(app.envPrefix);
+    const applies = switchesThatApply(app.allTools);
     const cache = app.allTools.some((tool) => tool.cache);
     const sync = app.allTools.some((tool) => tool.sync);
     const jobs = app.allTools.some((tool) => tool.job);
@@ -236,20 +237,24 @@ export function renderGeneralHelp(app, bin) {
     const tuning = [
         ...(app.definition.settings ?? []).filter((setting) => setting.tuning).map((setting) => setting.env),
         names.surface,
-        names.auditLog,
+        ...(applies.auditLog ? [names.auditLog] : []),
         names.toolTimeoutMs,
-        names.confirm,
+        ...(applies.confirm ? [names.confirm] : []),
         ...(cache ? [names.cache] : []),
         ...(cache || sync ? [names.dataDir] : []),
         `${app.envPrefix}_DEBUG`,
     ];
     const settings = [
         ...(app.definition.settings ?? []).filter((setting) => !setting.tuning).map((setting) => [setting.env, setting.description]),
-        [`${names.readOnly}=1`, "hide and refuse every write"],
-        [
-            `${names.allowDestructive}=0`,
-            `${app.definition.defaults?.destructiveOff === "hide" ? "hide and refuse" : "refuse"} the irreversible writes${app.allTools.some((tool) => tool.spends) ? " and paid calls" : ""}`,
-        ],
+        ...(applies.readOnly ? [[`${names.readOnly}=1`, "hide and refuse every write"]] : []),
+        ...(applies.allowDestructive
+            ? [
+                [
+                    `${names.allowDestructive}=0`,
+                    `${app.definition.defaults?.destructiveOff === "hide" ? "hide and refuse" : "refuse"} the irreversible writes${app.allTools.some((tool) => tool.spends) ? " and paid calls" : ""}`,
+                ],
+            ]
+            : []),
         // With no tagged tool every tool is always on, so the switch would do nothing.
         ...(app.allTools.some((tool) => tool.tags.length > 0) ? [[`${names.toolsets}=a,b`, "only these toolsets, or all"]] : []),
         [`${app.envPrefix}_HTTP_PORT / _HOST / _TOKEN / _ALLOWED_ORIGINS`, "for --http"],

package/dist/docs.js

@@ -7,7 +7,7 @@
  */
 import { flagsFor } from "./cli/flags.js";
 import { exampleCommand } from "./cli/help.js";
-import { policyEnvNames } from "./policy.js";
+import { policyEnvNames, switchesThatApply } from "./policy.js";
 function cell(text) {
     return text.replace(/\|/g, "\\|").replace(/\s*\n\s*/g, " ").trim() || "None";
 }
@@ -47,17 +47,22 @@ export function toolReference(app, tools, heading = "###") {
 }
 export function settingsTable(app) {
     const names = policyEnvNames(app.envPrefix);
+    const applies = switchesThatApply(app.allTools);
     return [
         "| Variable | What it does |",
         "|---|---|",
         ...(app.definition.settings ?? []).map((setting) => `| \`${setting.env}\` | ${cell(setting.description)}${setting.secret ? " Keep it private." : ""} |`),
-        `| \`${names.readOnly}=1\` | Hide and refuse every write |`,
-        `| \`${names.allowDestructive}=0\` | Keep writes, refuse the public or irreversible ones${app.allTools.some((tool) => tool.spends) ? " and paid calls" : ""} |`,
+        ...(applies.readOnly ? [`| \`${names.readOnly}=1\` | Hide and refuse every write |`] : []),
+        ...(applies.allowDestructive
+            ? [`| \`${names.allowDestructive}=0\` | Keep writes, refuse the public or irreversible ones${app.allTools.some((tool) => tool.spends) ? " and paid calls" : ""} |`]
+            : []),
         `| \`${names.toolsets}\` | Comma-separated toolsets to turn on, or \`all\` |`,
         `| \`${names.surface}=search\` | List three tools that find, describe and run the rest |`,
-        `| \`${names.auditLog}\` | File that records every attempted write |`,
+        ...(applies.auditLog ? [`| \`${names.auditLog}\` | File that records every attempted write |`] : []),
         `| \`${names.toolTimeoutMs}\` | Give up on any tool after this many milliseconds |`,
-        `| \`${names.confirm}=model\` | Let \`confirm: true\` alone confirm a call, for an agent with no person to ask. The default, \`human\`, asks a person wherever the client can |`,
+        ...(applies.confirm
+            ? [`| \`${names.confirm}=model\` | Let \`confirm: true\` alone confirm a call, for an agent with no person to ask. The default, \`human\`, asks a person wherever the client can |`]
+            : []),
     ].join("\n");
 }
 export function renderDocs(app, env = process.env) {

package/dist/policy.d.ts

@@ -62,6 +62,19 @@ export type PolicyEnv = {
     cache: string;
     dataDir: string;
 };
+/**
+ * Which of the write switches can change anything for these tools. A server
+ * whose tools all read has nothing for read-only mode to hide or the audit log
+ * to record, and one with no irreversible, paid or confirmed call has nothing
+ * for the destructive and confirm switches to act on, so help, agent-context
+ * and the generated docs leave those out. They still work if set.
+ */
+export declare function switchesThatApply(tools: readonly Tool[]): {
+    readOnly: boolean;
+    allowDestructive: boolean;
+    auditLog: boolean;
+    confirm: boolean;
+};
 export declare function policyEnvNames(prefix: string): PolicyEnv;
 export declare function readPolicy(env: NodeJS.ProcessEnv, prefix: string, defaults?: PolicyDefaults): Policy;
 export type Visibility = {

package/dist/policy.js

@@ -6,6 +6,22 @@
  * block the irreversible ones, keep a log, load fewer tools. They live under
  * the server's own prefix, so two servers in one client never share a switch.
  */
+/**
+ * Which of the write switches can change anything for these tools. A server
+ * whose tools all read has nothing for read-only mode to hide or the audit log
+ * to record, and one with no irreversible, paid or confirmed call has nothing
+ * for the destructive and confirm switches to act on, so help, agent-context
+ * and the generated docs leave those out. They still work if set.
+ */
+export function switchesThatApply(tools) {
+    const writes = tools.some((tool) => tool.risk !== "read");
+    return {
+        readOnly: writes,
+        allowDestructive: tools.some((tool) => tool.risk === "destructive" || tool.spends),
+        auditLog: writes,
+        confirm: tools.some((tool) => tool.requireConfirm),
+    };
+}
 export function policyEnvNames(prefix) {
     return {
         readOnly: `${prefix}_READ_ONLY`,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@thenavidm/slipway",
-  "version": "0.1.11",
+  "version": "0.1.12",
   "description": "Slipway, the TypeScript framework for MCP servers and agent-native CLIs. One tool definition ships an MCP server and a CLI, with write safety, typed results and release checks built in.",
   "type": "module",
   "license": "Apache-2.0",