---
title: "Call page.create"
method: POST
path: "/api/v1/tools/page.create"
tags: ["page"]
---

# Call page.create

`POST /api/v1/tools/page.create`

## Request

- Base URL: `https://app.goosybear.ai`
- URL: `https://app.goosybear.ai/api/v1/tools/page.create`
- Auth: HTTP bearer

Make a brand-new website — 'build me a site for my consultancy', 'I need a landing page', 'make a website for the new product'. Create a multi-page website from a blueprint — home, about and contact with working navigation and the full search/AI discovery file set. Describe what the site is for with intent, or leave it out to get starter copy with no paid generation. When the member asked for the site themselves in this conversation it creates it at once — report what the result says; only a site nobody asked for raises its approval card first, which is the member's confirmation, and then it can still be refused. It does NOT publish either: the site is built, not put on the internet, and if build_run_id is missing say the build has not started yet — quoting build_enqueue_error as the reason when it is present, and offering to try the build again. If draft_error comes back and source_ref does not, NOTHING WAS DRAFTED: the site exists and is openable but empty, so say exactly that, quote the reason, and offer to try again ON THAT site_id — never call page.create a second time for the same request, which would leave the member with two pages. Not for changing a site that already exists — that is `page.edit`. Over the API it answers in two calls: without confirmation_id it proposes — says what would happen, returns a confirmation_id and changes, spends and sends nothing; the same arguments again with that confirmation_id, on a member's own API key, do it.

Every result names the workspace it ran in. Say which workspace the answer is about. When the account has more than one workspace and none is selected, this tool refuses with `workspace_ambiguous` and lists the choices — offer them, never pick one.

## Headers

- `x-request-id` string

## Request body

- object
  - `name` string: Optional name for the site. Leave it out to take the default.
  - `intent` string: What this site is for, in the operator's own terms. Leave it out to get the blueprint's starter copy with no paid generation. Do not invent claims, offers or statistics. A site generated from the general-marketing template carries a lead-capture form on its landing page — email and name, with a consent line — so a request for one is met by creating the site and needs nothing here; anything else about the form (extra fields, different wording, moving it, or taking it off) is a page.edit once the site exists. Two states where a new site does NOT show one, and neither is a reason to tell the member they cannot have a form: a site copied from a saved blueprint carries whatever form that blueprint had, which may be none, and a form saved as `enabled: false` is stored but not rendered. In both cases a page.edit puts one on any page. IGNORED when blueprint_id names one of this workspace's saved blueprints: that path copies the saved template verbatim and runs no generation, so say the copy ran unchanged rather than implying these words shaped it.
  - `blueprint_id` string: Which blueprint to start from — a first-party template id or one of this workspace's own saved blueprint ids, both listed by page.list with list 'templates'. Starting from a saved blueprint copies that template and runs no generation. Leave it out for the default general marketing site; an unknown id is refused server-side.
  - `inspiration_url` string: Optional full https:// link to a site to take structural inspiration from. Its wording and offers are never reproduced. IGNORED when blueprint_id names one of this workspace's saved blueprints — that path copies a saved template and takes structure from nothing else.
  - `confirmation_id` string, uuid: Omit to propose: the first call says what would happen, returns a confirmation_id and changes nothing. To go ahead, send the same arguments again with that confirmation_id, on a member's own API key; a service account's key can propose but never confirm.
  - `workspace` string: Which workspace to run in — its slug. Omit to use your default. With more than one reachable workspace and no default, the call is refused and the choices are listed.

## Response `200`

The call was admitted and dispatched. `ok` says whether the tool succeeded — a refusal the tool itself produced is still a 200, exactly as it is a successful JSON-RPC result over MCP.

- union
  - object: The tool ran and answered.
    - `ok` true, required
    - `state` 'confirmation_required'
    - `confirmation_id` string, uuid
    - `expires_in_seconds` integer
    - `request_summary` string: What will happen, in one sentence, for a person to approve before confirming.
    - `site_id` string, uuid
    - `name` string
    - `blueprint_id` string
    - `source_ref` string
    - `draft_error` string
    - `build_run_id` string
    - `build_enqueue_error` string
    - `workspace` string, required: The slug of the workspace this call ran in.
    - `working_in` object, required: Which workspace this call ran in, and how that was decided. Present on every workspace-scoped result.
      - `label` string, required: The chip words — e.g. "working in: Acme Main".
      - `note` string, required: Why this workspace — e.g. "your default", "this call only".
      - `workspace` string, required: The resolved workspace's slug.
      - `source` 'call-override' | 'key-pin' | 'stored-default' | 'sole-reachable', required: Which rung of the R7 precedence resolved the workspace.
  - ToolRefusal: A call that was admitted and dispatched, and did not succeed.
    - `ok` false, required
    - `code` string, required: The typed reason — e.g. `workspace_ambiguous`, `invalid_arguments`, or the tool's own failure code.
    - `message` string, required: A sentence a person can act on.
    - `workspaces` string[]: On a workspace refusal: the slugs this key may pass as `workspace`.
    - `issues` object[]: On `invalid_arguments`: which fields failed, and why.
      - `path` string, required
      - `message` string, required
    - `path` string: On an authoring refusal: where in your call's input it points, e.g. `steps.<key>.params.<field>`.
    - `fix` string: On an authoring refusal: the change to your call that would pass.
    - `instruction` string: On an authoring refusal: what to do next with it.

## Other responses

- `400`: The request could not be used: the body is present but not a JSON object (`tenant_api.malformed_body`); it is a top-level array carrying more messages than this endpoint accepts (`tenant_mcp.batch_too_large`); or the `Idempotency-Key` header is malformed (`tenant_api.idempotency_key_invalid`), disagrees with the body's `idempotency_key` (`tenant_api.idempotency_key_conflict`), or was sent to an action that cannot replay a retry (`tenant_api.idempotency_unsupported`). Nothing ran.
- `401`: No bearer credential, or one that did not resolve. Deliberately ONE undifferentiated answer for absent / unknown / revoked / expired, so the endpoint is never an oracle over the key space.
- `403`: The credential is good but the surface is not open to it — the platform or account API switch is off, or the holder lacks the `api.access` capability. The `code` says which.
- `404`: No such tool. The body names no tool and is identical for every unrecognised name.
- `429`: Over this key's per-minute cap. Carries `Retry-After` and `error.retry_after_seconds`.

---

[API](https://skmtc.dev/goosybear/apis/goosy-bear-api.md) · [All operations](https://skmtc.dev/goosybear/apis/goosy-bear-api/llms.txt) · [OpenAPI document](https://skmtc.dev/goosybear/apis/goosy-bear-api/revisions/6d82fb124064?raw)