@cloudgrid-io/mcp 0.16.2 → 0.18.0

package/src/corpus/workflows/semantic-search.md

@@ -6,7 +6,7 @@ deploy: runtime
 editions: local
 capabilities_note: "Document search — needs a database (Mongo) for the documents + chunks collections. Two services: a React (Vite) static frontend at / and a FastAPI backend at /backend. Hybrid search = Mongo $text (lexical) + in-app NumPy cosine over chunk embedding arrays (semantic) + metadata filters, blended to the document level. Runtime app, async build, local edition only. Declare needs:{database:true}. NO needs:vector — pgvector runtime role-grant is blocked (#1545), so embeddings live in the Mongo chunks collection and are cosine-ranked in-app. Two refresh paths: the manager 'Refresh now' endpoint AND a scheduled Python type:cron job (services/refresh, daily 03:00 UTC) that vendors the backend app/ modules and reuses indexing.run_sync — both degrade gracefully. Health is green with no secrets; startup ensure_indexes() so $text never 500s on an empty catalog. Pluggable source (dropbox|local|url) + embeddings (OpenAI-compatible) each behind one config point, all secrets from env."
 summary: "Build a document-search app on the grid — index a folder of PDFs/DOCX/TXT/MD, then search by keyword + meaning + metadata, with a grounded answer mode and manager admin. React static frontend at / + FastAPI backend at /backend, backed by grid-shared Mongo. Edition-gate first, scaffold, put the code under services/web/ + services/backend/, declare needs:{database:true} (NO vector #1545), wire the web+backend+refresh services, set the embeddings + source + manager secrets, deploy async, poll to a live URL, then Refresh now (or wait for the daily cron) to index."
-recipe: "edition-gate -> auth+grid -> gridctl_init -> fetch template + read AGENTS.md -> put code under services/web + services/backend, set cloudgrid.yaml active fields -> grid secrets set (embeddings + source + MANAGER_PASSWORD_HASH) -> optional grid dev -> grid plug (async, poll) -> Refresh now to index -> return live URL"
+recipe: "edition-gate -> auth+grid -> grid_init -> fetch template + read AGENTS.md -> put code under services/web + services/backend, set cloudgrid.yaml active fields -> grid secrets set (embeddings + source + MANAGER_PASSWORD_HASH) -> optional grid dev -> grid plug (async, poll) -> Refresh now to index -> return live URL"
 ---
 
 # Workflow: semantic-search
@@ -36,19 +36,19 @@ the **local edition** (Claude Desktop / Claude Code) or the CLI.
 
 ## 2. Auth + grid
 
-1. Ensure signed in: `gridctl_login_status`; if not, `gridctl_login`.
+1. Ensure signed in: `grid_login_status`; if not, `grid_login`.
 2. A grid is required. Respect the grid picker: if the user has more than one
    grid, ask which to use; do not assume a target.
 
 ## 3. Scaffold
 
-`gridctl_init` an app `<name>` FIRST — it creates the entity +
+`grid_init` an app `<name>` FIRST — it creates the entity +
 `.cloudgrid/link.json` and a starter `cloudgrid.yaml` with empty `services: {}`
 (`plug` needs a linked directory).
 
 ## 4. Fetch the template and READ AGENTS.md
 
-`gridctl_fetch("template", "semantic-search")`. Read **`AGENTS.md`** before
+`grid_fetch("template", "semantic-search")`. Read **`AGENTS.md`** before
 writing anything — it defines the file tree, the `documents` + `chunks`
 collections + fields, the Mongo injection, the pluggable source adapter, the
 embeddings config point, the secrets, the deploy flow, and the four baked-in
@@ -111,7 +111,7 @@ the cron **vendors** the backend `app/` modules it needs into
 
 Store all of these with `grid secrets set KEY=VALUE` (never commit them; the app
 reads them lazily inside functions, never at import). Non-secret public config →
-`gridctl_env`. Do NOT set `DATABASE_MONGODB_URL` yourself — the grid injects it.
+`grid_env`. Do NOT set `DATABASE_MONGODB_URL` yourself — the grid injects it.
 
 The app starts and passes `GET /backend/health` with **none** of these set;
 search/indexing degrade to a clear "not indexed / missing secret" state.
@@ -123,9 +123,9 @@ before deploying. Don't require it.
 
 ## 8. Deploy (async)
 
-Deploy the folder with `gridctl_plug`. A **runtime deploy is ASYNC**: the first
+Deploy the folder with `grid_plug`. A **runtime deploy is ASYNC**: the first
 response is `status: "building"`, NOT a live URL yet.
-- Poll `gridctl_status` (or the returned poll_url) until the entity is live.
+- Poll `grid_status` (or the returned poll_url) until the entity is live.
 - Surface a liveness signal while it builds — never a bare silent wait.
 - Only once it is live, return the deployed app URL (NOT the build/log link).
 

package/src/corpus/workflows/status-page.md

@@ -4,7 +4,7 @@ when: status page, service status, uptime page, incident history, is-it-down pag
 needs: none
 deploy: inspiration
 editions: all
-capabilities_note: static — no infrastructure, status baked into the page. Publishes as an inspiration (instant, works on hosted) via gridctl_drop.
+capabilities_note: static — no infrastructure, status baked into the page. Publishes as an inspiration (instant, works on hosted) via grid_plug.
 summary: Fetch the status-page template, fill it with the user's components and incidents, deploy it, and return the live share URL.
 ---
 
@@ -15,7 +15,7 @@ recipe. This is a display-only static page — the status is baked into the mark
 there is no live polling. Do not ask setup questions first; use sensible defaults
 and build.
 
-1. **Fetch the template.** Call `gridctl_fetch("template", "status-page")` to load
+1. **Fetch the template.** Call `grid_fetch("template", "status-page")` to load
    the self-contained HTML status page (overall banner, component list with
    up/degraded/down pills, per-component uptime bars, incident history).
 2. **Fill the template.** Replace the placeholders with the user's content:
@@ -27,7 +27,7 @@ and build.
      stylesheets, fonts, or large embedded media.
 3. **Deploy.** Deploy the filled HTML:
    - Hosted MCP edition: call the drop tool with the HTML.
-   - Local MCP / CLI edition: write the HTML to a file and run `gridctl plug`.
+   - Local MCP / CLI edition: write the HTML to a file and run `grid plug`.
    It is an inspiration and deploys synchronously, so you get a URL right away.
 4. **Return the live share URL.** For revisions, re-deploy with the entity id
    from the first deploy — it updates the same share URL.

package/src/corpus/workflows/subscription-management.md

@@ -40,7 +40,7 @@ A subscription-management app is a built + deployed container. It requires the
 
 ## 2. Auth + grid
 
-1. Ensure signed in: `gridctl_login_status`; if not, `gridctl_login`.
+1. Ensure signed in: `grid_login_status`; if not, `grid_login`.
 2. A grid is required. Respect the grid picker: if the user has more than one
    grid, ask which to use; do not assume a target.
 
@@ -49,18 +49,18 @@ A subscription-management app is a built + deployed container. It requires the
 Fetch the template and read its structure guide — this is the core of the
 workflow:
 
-- `gridctl_fetch("template", "subscription-management")` — the `cloudgrid.yaml` +
+- `grid_fetch("template", "subscription-management")` — the `cloudgrid.yaml` +
   **`AGENTS.md`**. AGENTS.md has the file tree, the Mongo collections
   (`customers`, `subscriptions`), the CloudGrid injection table, and the Stripe
   change-plan / cancel / billing-portal / webhook wiring. **Read it fully before
   building.**
-- `gridctl_fetch("template", "app-with-data")` — the proven Next.js + Mongo
+- `grid_fetch("template", "app-with-data")` — the proven Next.js + Mongo
   shape this blueprint extends (lazy db client in `lib/db.js`, App-Router
   GET/POST route). Imitate its wiring.
 
 ## 4. Scaffold
 
-`gridctl_init` an app `<name>`. `init` creates the entity + `.cloudgrid/link.json`
+`grid_init` an app `<name>`. `init` creates the entity + `.cloudgrid/link.json`
 and writes a `cloudgrid.yaml` with an EMPTY `services: {}`. `plug` needs a linked
 directory, so run `init` FIRST. Then write the app under **`services/web/`** and
 set `cloudgrid.yaml` to the active shape below.
@@ -109,12 +109,12 @@ never set `needs:` and `requires:` together (the validator rejects it).
 
 ## 6. Config / secrets
 
-- Stripe secrets → `gridctl_secrets` (set the vault items `stripe-live-key` and
+- Stripe secrets → `grid_secrets` (set the vault items `stripe-live-key` and
   `stripe-webhook-secret` that the `vault:` block maps from). The deployer
   injects each as its env var at runtime and under `grid dev`. Add
   `auth-provider-key` too if you use an auth SDK.
 - Non-secret config (Stripe publishable key `NEXT_PUBLIC_STRIPE_PUBLISHABLE_KEY`,
-  price ids, auth publishable key) → `gridctl_env` / `services.web.env`.
+  price ids, auth publishable key) → `grid_env` / `services.web.env`.
 - Do **NOT** set the DB connection vars yourself (`DATABASE_MONGODB_URL` / legacy
   `MONGODB_URL`) — the grid injects them.
 
@@ -125,9 +125,9 @@ and vault secrets before deploying. Don't require it.
 
 ## 8. Deploy (async)
 
-Deploy the folder with `gridctl_plug`. A **runtime deploy is ASYNC**: the first
+Deploy the folder with `grid_plug`. A **runtime deploy is ASYNC**: the first
 response is `status: "building"`, NOT a live URL yet.
-- Poll `gridctl_status` (or the returned poll_url) until the entity is live.
+- Poll `grid_status` (or the returned poll_url) until the entity is live.
 - Surface a liveness signal while it builds — never a bare silent wait.
 - Once live, register the `/api/webhook` URL as the Stripe webhook endpoint,
   copy the signing secret into the `stripe-webhook-secret` vault item, configure

package/src/corpus/workflows/task-manager.md

@@ -33,13 +33,13 @@ edition** (Claude Desktop / Claude Code) or the CLI.
 
 ## 2. Auth + grid
 
-1. Ensure signed in: `gridctl_login_status`; if not, `gridctl_login`.
+1. Ensure signed in: `grid_login_status`; if not, `grid_login`.
 2. A grid is required. Respect the grid picker: if the user has more than one
    grid, ask which to use; do not assume a target.
 
 ## 3. Scaffold
 
-`gridctl_init` an app `<name>`. `init` creates the entity + `.cloudgrid/link.json`
+`grid_init` an app `<name>`. `init` creates the entity + `.cloudgrid/link.json`
 and writes a `cloudgrid.yaml` with an EMPTY `services: {}`. `plug` needs a linked
 directory, so run `init` FIRST. Then (a) write the app under **`services/web/`**,
 and (b) fill `cloudgrid.yaml` to the shape below (`services.web` + `needs:
@@ -64,7 +64,7 @@ and (b) fill `cloudgrid.yaml` to the shape below (`services.web` + `needs:
    author new yaml with it, and never set `needs:` and `requires:` together (the
    validator rejects it).
 2. Fetch the template for the Mongo wiring + CRUD shape:
-   `gridctl_fetch("template", "task-manager")`. It is a minimal, real Next.js +
+   `grid_fetch("template", "task-manager")`. It is a minimal, real Next.js +
    `mongodb`-driver task manager under `services/web/`: a lazy client in
    `services/web/lib/db.js`, an App-Router GET/POST/PATCH/DELETE route on a
    `tasks` collection (PATCH toggles done), a server-component page, and a client
@@ -82,15 +82,15 @@ before deploying. Don't require it.
 
 ## 6. Config
 
-- API keys / secrets → `gridctl_secrets`. Non-secret config → `gridctl_env`.
+- API keys / secrets → `grid_secrets`. Non-secret config → `grid_env`.
 - Do **NOT** set the DB connection vars yourself (`DATABASE_MONGODB_URL` or the
   legacy `MONGODB_URL`) — the grid injects them.
 
 ## 7. Deploy (async)
 
-Deploy the folder with `gridctl_plug`. A **runtime deploy is ASYNC**: the first
+Deploy the folder with `grid_plug`. A **runtime deploy is ASYNC**: the first
 response is `status: "building"`, NOT a live URL yet.
-- Poll `gridctl_status` (or the returned poll_url) until the entity is live.
+- Poll `grid_status` (or the returned poll_url) until the entity is live.
 - Surface a liveness signal while it builds — never a bare silent wait.
 - Only once it is live, return the deployed app URL (NOT the build/log link).
 

package/src/corpus/workflows/ticket-system.md

@@ -31,13 +31,13 @@ edition** (Claude Desktop / Claude Code) or the CLI.
 
 ## 2. Auth + grid
 
-1. Ensure signed in: `gridctl_login_status`; if not, `gridctl_login`.
+1. Ensure signed in: `grid_login_status`; if not, `grid_login`.
 2. A grid is required. Respect the grid picker: if the user has more than one
    grid, ask which to use; do not assume a target.
 
 ## 3. Scaffold
 
-`gridctl_init` an app `<name>`. `init` creates the entity + `.cloudgrid/link.json`
+`grid_init` an app `<name>`. `init` creates the entity + `.cloudgrid/link.json`
 and writes a `cloudgrid.yaml` with an EMPTY `services: {}`. `plug` needs a linked
 directory, so run `init` FIRST. Then (a) write the app under **`services/web/`**,
 and (b) fill `cloudgrid.yaml` to the shape below (`services.web` + `needs:
@@ -65,7 +65,7 @@ and (b) fill `cloudgrid.yaml` to the shape below (`services.web` + `needs:
    `services.web`, and `needs.database` uncommented — so it deploys to exactly
    those active fields.
 2. Fetch the template for the Mongo wiring + CRUD shape:
-   `gridctl_fetch("template", "ticket-system")`. It is a minimal, real Next.js +
+   `grid_fetch("template", "ticket-system")`. It is a minimal, real Next.js +
    `mongodb`-driver app under `services/web/`: a lazy client in
    `services/web/lib/db.js`, an App-Router GET/POST/PATCH (status)/DELETE route on a `tickets` collection, a
    server-component page, and a client component.
@@ -82,15 +82,15 @@ before deploying. Don't require it.
 
 ## 6. Config
 
-- API keys / secrets → `gridctl_secrets`. Non-secret config → `gridctl_env`.
+- API keys / secrets → `grid_secrets`. Non-secret config → `grid_env`.
 - Do **NOT** set the DB connection vars yourself (`DATABASE_MONGODB_URL` or the
   legacy `MONGODB_URL`) — the grid injects them.
 
 ## 7. Deploy (async)
 
-Deploy the folder with `gridctl_plug`. A **runtime deploy is ASYNC**: the first
+Deploy the folder with `grid_plug`. A **runtime deploy is ASYNC**: the first
 response is `status: "building"`, NOT a live URL yet.
-- Poll `gridctl_status` (or the returned poll_url) until the entity is live.
+- Poll `grid_status` (or the returned poll_url) until the entity is live.
 - Surface a liveness signal while it builds — never a bare silent wait.
 - Only once it is live, return the deployed app URL (NOT the build/log link).
 

package/src/corpus/workflows/time-tracking.md

@@ -32,13 +32,13 @@ edition** (Claude Desktop / Claude Code) or the CLI.
 
 ## 2. Auth + grid
 
-1. Ensure signed in: `gridctl_login_status`; if not, `gridctl_login`.
+1. Ensure signed in: `grid_login_status`; if not, `grid_login`.
 2. A grid is required. Respect the grid picker: if the user has more than one
    grid, ask which to use; do not assume a target.
 
 ## 3. Scaffold
 
-`gridctl_init` an app `<name>`. `init` creates the entity + `.cloudgrid/link.json`
+`grid_init` an app `<name>`. `init` creates the entity + `.cloudgrid/link.json`
 and writes a `cloudgrid.yaml` with an EMPTY `services: {}`. `plug` needs a linked
 directory, so run `init` FIRST. Then (a) write the app under **`services/web/`**,
 and (b) fill `cloudgrid.yaml` to the shape below (`services.web` + `needs:
@@ -63,7 +63,7 @@ and (b) fill `cloudgrid.yaml` to the shape below (`services.web` + `needs:
    author new yaml with it, and never set `needs:` and `requires:` together (the
    validator rejects it).
 2. Fetch the template for the Mongo wiring + CRUD shape:
-   `gridctl_fetch("template", "time-tracking")`. It is a minimal, real Next.js +
+   `grid_fetch("template", "time-tracking")`. It is a minimal, real Next.js +
    `mongodb`-driver time tracker under `services/web/`: a lazy client in
    `services/web/lib/db.js`, an App-Router GET/POST/DELETE route on an `entries`
    collection, a server-component page, and a client form that also renders
@@ -85,15 +85,15 @@ before deploying. Don't require it.
 
 ## 6. Config
 
-- API keys / secrets → `gridctl_secrets`. Non-secret config → `gridctl_env`.
+- API keys / secrets → `grid_secrets`. Non-secret config → `grid_env`.
 - Do **NOT** set the DB connection vars yourself (`DATABASE_MONGODB_URL` or the
   legacy `MONGODB_URL`) — the grid injects them.
 
 ## 7. Deploy (async)
 
-Deploy the folder with `gridctl_plug`. A **runtime deploy is ASYNC**: the first
+Deploy the folder with `grid_plug`. A **runtime deploy is ASYNC**: the first
 response is `status: "building"`, NOT a live URL yet.
-- Poll `gridctl_status` (or the returned poll_url) until the entity is live.
+- Poll `grid_status` (or the returned poll_url) until the entity is live.
 - Surface a liveness signal while it builds — never a bare silent wait.
 - Only once it is live, return the deployed app URL (NOT the build/log link).
 

package/src/corpus/workflows/travel-booking.md

@@ -40,18 +40,18 @@ edition** (Claude Desktop / Claude Code) or the CLI.
 
 ## 2. Auth + grid
 
-1. Ensure signed in: `gridctl_login_status`; if not, `gridctl_login`.
+1. Ensure signed in: `grid_login_status`; if not, `grid_login`.
 2. A grid is required. Respect the grid picker: if the user has more than one
    grid, ask which to use; do not assume a target.
 
 ## 3. Read the blueprint, then scaffold
 
-1. Fetch the blueprint: `gridctl_fetch("template", "travel-booking")`. **Read its
+1. Fetch the blueprint: `grid_fetch("template", "travel-booking")`. **Read its
    `AGENTS.md`** — it is the structure guide (file tree under `services/web/`, the
    `flights` / `hotels` / `bookings` / `trips` collections + the overbooking
    guard, how CloudGrid injects the DB and vault secrets, how to wire Stripe +
    auth, and the trip-reminder-cron design).
-2. `gridctl_init` an app `<name>`. `init` creates the entity + `.cloudgrid/link.json`
+2. `grid_init` an app `<name>`. `init` creates the entity + `.cloudgrid/link.json`
    and writes a `cloudgrid.yaml` with an EMPTY `services: {}`. `plug` needs a
    linked directory, so run `init` FIRST.
 
@@ -88,9 +88,9 @@ edition** (Claude Desktop / Claude Code) or the CLI.
 
 ## 5. Config (secrets)
 
-- Payment/auth secrets → add the vault items with `gridctl_secrets` (e.g.
+- Payment/auth secrets → add the vault items with `grid_secrets` (e.g.
   `stripe-live-key`, `stripe-webhook-secret`, `auth-provider-key`) BEFORE plug so
-  the `vault:` mappings resolve. Non-secret config → `gridctl_env`.
+  the `vault:` mappings resolve. Non-secret config → `grid_env`.
 - Do **NOT** set the DB connection vars yourself (`DATABASE_MONGODB_URL` / legacy
   `MONGODB_URL`) — the grid injects them.
 
@@ -102,9 +102,9 @@ require it.
 
 ## 7. Deploy (async)
 
-Deploy the folder with `gridctl_plug`. A **runtime deploy is ASYNC**: the first
+Deploy the folder with `grid_plug`. A **runtime deploy is ASYNC**: the first
 response is `status: "building"`, NOT a live URL yet.
-- Poll `gridctl_status` (or the returned poll_url) until the entity is live.
+- Poll `grid_status` (or the returned poll_url) until the entity is live.
 - Surface a liveness signal while it builds — never a bare silent wait.
 - Only once it is live, return the deployed app URL (NOT the build/log link).
 

package/src/corpus/workflows/waitlist.md

@@ -4,7 +4,7 @@ when: waitlist, coming soon, early access, join the list, launch page, sign-up t
 needs: none
 deploy: inspiration
 editions: all
-capabilities_note: static — no infrastructure. The email form posts to a configurable mailto/external endpoint; it does NOT store signups. Publishes as an inspiration (instant, works on hosted) via gridctl_drop.
+capabilities_note: static — no infrastructure. The email form posts to a configurable mailto/external endpoint; it does NOT store signups. Publishes as an inspiration (instant, works on hosted) via grid_plug.
 summary: Fetch the waitlist template, fill it with the user's launch copy, wire the form to a mailto or external endpoint, deploy it, and return the live share URL.
 ---
 
@@ -22,7 +22,7 @@ NOT store signups anywhere on CloudGrid. To actually **store** waitlist signups
 (`needs: { database: true }`) — that is a CRUD app, coming in the crud-app
 archetype (Wave 1b). Do not claim this static page persists data.
 
-1. **Fetch the template.** Call `gridctl_fetch("template", "waitlist")` to load
+1. **Fetch the template.** Call `grid_fetch("template", "waitlist")` to load
    the self-contained HTML waitlist page (hero, email form, social-proof counter).
 2. **Fill the template.** Replace the placeholders with the user's content:
    - The product name, coming-soon headline, and subheadline.
@@ -33,7 +33,7 @@ archetype (Wave 1b). Do not claim this static page persists data.
      stylesheets, fonts, or large embedded media.
 3. **Deploy.** Deploy the filled HTML:
    - Hosted MCP edition: call the drop tool with the HTML.
-   - Local MCP / CLI edition: write the HTML to a file and run `gridctl plug`.
+   - Local MCP / CLI edition: write the HTML to a file and run `grid plug`.
    It is an inspiration and deploys synchronously, so you get a URL right away.
 4. **Return the live share URL.** For revisions, re-deploy with the entity id
    from the first deploy — it updates the same share URL. If the user needs

package/src/corpus/workflows/web-app.md

@@ -4,7 +4,7 @@ when: calculator, converter, generator, timer, quiz, interactive tool, mini-app,
 needs: none
 deploy: inspiration
 editions: all
-capabilities_note: static — no infrastructure, state lives only in memory. Publishes as an inspiration (instant, works on hosted) via gridctl_drop.
+capabilities_note: static — no infrastructure, state lives only in memory. Publishes as an inspiration (instant, works on hosted) via grid_plug.
 summary: Fetch the web-app template, adapt its markup and inline JS to the user's tool, deploy it, and return the live share URL.
 ---
 
@@ -14,9 +14,9 @@ Detect the intent ("build me a web app / tool / calculator that does X") and
 follow this recipe. Do not ask setup questions first; use sensible defaults and
 build.
 
-1. **Fetch the template.** Call `gridctl_fetch("template", "web-app")` to load
+1. **Fetch the template.** Call `grid_fetch("template", "web-app")` to load
    the self-contained interactive HTML app template.
-2. **(Optional) Fetch the example.** Call `gridctl_fetch("example", "web-app")`
+2. **(Optional) Fetch the example.** Call `grid_fetch("example", "web-app")`
    to see a real working tool as a reference for structure and inline logic.
 3. **Adapt the template.** Rework the markup and inline JavaScript into the tool
    the user asked for:
@@ -27,7 +27,7 @@ build.
      stylesheets, fonts, or CDNs — inline everything.
 4. **Deploy.** Deploy the filled HTML:
    - Hosted MCP edition: call the drop tool with the HTML.
-   - Local MCP / CLI edition: write the HTML to a file and run `gridctl plug`.
+   - Local MCP / CLI edition: write the HTML to a file and run `grid plug`.
    A web app is an inspiration and deploys synchronously, so you get a URL
    right away.
 5. **Return the live share URL.** Give the user the URL that serves the app.

package/src/docs.js

@@ -39,18 +39,18 @@ function ok(text) {
 function createDocsServer() {
   const server = new McpServer({ name: "cloudgrid-docs", version });
 
-  // Naming cleanup (spec §6): the docs tools move to the gridctl_* family. Both
+  // Naming cleanup (spec §6): the docs tools move to the grid_* family. Both
   // legacy names stay registered as deprecated aliases (same handler) so nothing
   // breaks mid-migration; aliases are removed in a later major.
-  //   search_cloudgrid_documentation → gridctl_search_docs
-  //   cloudgrid_quickstart_guide     → gridctl_quickstart
+  //   search_cloudgrid_documentation → grid_search_docs
+  //   cloudgrid_quickstart_guide     → grid_quickstart
   const dual = (name, alias, description, schema, handler) => {
     server.tool(name, description, schema, handler);
     server.tool(alias, `(deprecated: use ${name}) ${description}`, schema, handler);
   };
 
   dual(
-    "gridctl_search_docs",
+    "grid_search_docs",
     "search_cloudgrid_documentation",
     "Search CloudGrid documentation — guides, tutorials, CLI reference, MCP setup, and skill descriptions. Returns the most relevant doc chunks with title, snippet, and source path.",
     {
@@ -75,7 +75,7 @@ function createDocsServer() {
   );
 
   dual(
-    "gridctl_quickstart",
+    "grid_quickstart",
     "cloudgrid_quickstart_guide",
     "Get the CloudGrid quickstart guide — the canonical build-and-ship loop from scaffold to deploy to feedback.",
     {},

package/src/index.js

@@ -32,7 +32,7 @@ const server = new McpServer({ name: "cloudgrid-mcp", version });
 registerTools(server, ctx);
 
 // Capture the calling agent's clientInfo (name+version) once the MCP handshake
-// completes, so gridctl_report can attribute the report's origin (which agent).
+// completes, so grid_report can attribute the report's origin (which agent).
 // getClientVersion() is populated by the SDK from the initialize request's
 // clientInfo. Never fatal — a missing client just falls back to "unknown".
 server.server.oninitialized = () => {