add_task_history
ChatGPTAppend a history record to a task. This is the primary way to report progress, add notes, store handover snippets, or attach architecture documents. Never overwrites existing state — fully append-only.
configure_form
ChatGPTDefine or update a form for a published website. Sets required fields and what actions execute on submit. Use action for a single action, or actions (array, max 3) for multiple in sequence. Built-in action (no setup needed): {\"type\": \"leads\"} — stores submissions in platform-native lead capture, retrievable via get_integration_schema on the "leads" service. External actions: {\"type\": \"iapi\", \"service\": \"resend\", ...} for email, or {\"type\": \"webhook\", \"url\": \"...\"}. The visitor only sends field values — actions are locked server-side. Use list_integrations to check available external services. IMPORTANT: When generating the JavaScript snippet for the page, always use the Safari ITP-proof pattern: store session_id in sessionStorage and send it as X-Session-Id header on both the session GET and form submit fetch calls. This is required for custom domains (e.g. www.site.com) where Safari blocks third-party cookies.
configure_visitor_auth
ChatGPTConfigure visitor authentication for a published website. Enables email-based login (magic link or 6-digit code) for website visitors. Required before visitors can authenticate. Use method "link" for one-click email login, "code" for a 6-digit verification code.
create_edit_session
ChatGPTCreates a visual edit session so the user can upload and manage images on their published page using a browser-based editor. Returns an edit URL to share with the user. When creating pages with images, use data-wpe-slot placeholder images instead of base64 — then create an edit session so the user can upload real images.
create_entity
ChatGPTCreate a new entity (data model). Example: create a "blogpost" entity with title, content, author fields.
create_fragment
ChatGPTCreate a reusable HTML fragment. Returns include_tag to embed in pages: <!--#wps-include fragment="name" -->. Use for shared elements like nav, footer, banners.
create_page
ChatGPTCreate a new page with HTML content. Tip: use <!--#wps-include fragment="name" --> to embed reusable fragments (nav, footer). Create fragments first with create_fragment.
create_project
ChatGPTCreate a new project for the user. Each project is an independent website with its own pages, assets, entities, and subdomain. Respects plan limits (Free: 1 project, Starter: 3, Pro: 10, Agency: unlimited). Returns the new project_id and subdomain.
create_record
ChatGPTCreate a new record in an entity. Fields depend on the entity schema.
create_scheduled_task
ChatGPTCreate a scheduled task that runs automatically at specified times. Supports cron expressions for flexible scheduling. Use run_once=true for one-time scheduled actions (e.g., publish a page at a specific date/time). Common cron patterns: "0 9 " (daily 9am), "0 9 1" (Monday 9am), "0 /6 " (every 6h), "0 0 1 1 " (Jan 1st midnight).
create_task
ChatGPTCreate a new task item in the shared task tracker. Use descriptive slugs like "sapi-fase4" or "capi-intake-redesign".
delete_asset
ChatGPTDelete an asset
delete_entity
ChatGPTDelete an entity and ALL its data. This action cannot be undone!
delete_fragment
ChatGPTDelete a reusable HTML fragment. Pages using its include_tag will render an empty string in its place.
delete_page
ChatGPTDelete a page
delete_record
ChatGPTDelete a record by ID
delete_scheduled_task
ChatGPTDelete a scheduled task and all its run history.
entities
ChatGPTManage MAPI entities (schema level — like database tables). Single entry point — pick an operation. list = all entities in the project. create = entity_name(+properties[], description?, plural?, public_read?). update = entity_name + any of description/plural/public_read/policy_json. delete = entity_name — irreversible, drops all data. schema = entity_name → full property list + current policy. add_property = entity_name+property_name+type(+length?,required?,default?,in_listing?) — add a column to an existing entity. delete_property = entity_name+property_name+confirm:true — irreversible, drops the column and its data.
execute_integration
ChatGPTExecute an integration action — e.g., send an email via Resend, create a payment via Mollie. The system resolves vault credentials server-side so you never handle API keys directly. The integration must be configured first via setup_integration (not needed for built-in integrations). Call get_integration_schema first to get the exact endpoint name and required input fields.
export_tasks
ChatGPTGenerate a Markdown overview of all tasks grouped by status (in_progress, blocked, open, null, done) with completion percentages. Tasks without history appear under "Geen status". Includes recent activity from today and yesterday. Use this at the start of a session for a quick backlog overview, or to share current status.
fragments
ChatGPTManage reusable HTML fragments (shared nav, footer, banners) embedded via <!--#wps-include fragment="name" -->. Single entry point — pick an operation. list = all fragments + versions. create = name+content. update = name+content, full replace (supports base_version_hash optimistic lock + force). patch = name+patches, targeted find/replace, efficient for small edits, preserves version history. delete = name. versions = name → version history. rollback = name + target_version|target_version_hash. All changes invalidate cache automatically.
get_analytics
ChatGPTGet visitor analytics for a project. Returns pageview counts, unique visitors, top pages, referrers, device breakdown, UTM data, or daily trend. Use period "today", "7d", "30d", or "90d".
get_asset
ChatGPTRead the full content of an existing asset so you can inspect it before patching. Text assets (js, css, json, svg, txt, html) are returned as UTF-8 strings in content with encoding: "utf-8". Binary assets (images, fonts, pdf) are returned as base64 in content with encoding: "base64", but only if size ≤ 1MB; above that the content is omitted and you should use the url field to download directly. Always returns version_hash (md5 of raw bytes) for future optimistic concurrency in patch_asset.
get_edit_session_changes
ChatGPTReads back what the user changed during a visual edit session. Returns a structured changelog with uploaded images, dimensions, style changes, etc. Use this after sharing the edit URL with the user to see what they did.
get_entity_schema
ChatGPTGet the schema definition of an entity, including all its properties and their types
get_integration_schema
ChatGPTGet the full schema of a specific integration: all available endpoints, required fields, and input parameters. Call this before execute_integration to know exactly how to call an endpoint. Use list_integrations first to see which integrations are available.
get_page
ChatGPTGet a specific page with its content. Returns version and version_hash for use with patch_page.
get_page_versions
ChatGPTGet the version history of a page. Returns metadata (version numbers, hashes, timestamps, change summaries) — no content. Useful to check what changed or find a version to rollback to.
get_project_status
ChatGPTGet detailed status of a specific project including page, asset, and entity counts
get_record
ChatGPTGet a single record by ID
get_skill
ChatGPTALWAYS call this tool at the start of every conversation where you will build or modify a WebsitePublisher website. Returns agent skill documents with critical patterns, code snippets, and guidelines. Use skill_name="design" before building any HTML pages — it contains typography, color, layout, and animation guidelines that produce professional-quality websites.
get_started
ChatGPTUse first when the person wants to build, change or publish a site, page, shop or app. No arguments. Returns the person's projects with their live URLs, which project to build in, and the exact next call that puts a page live. Read-only.
get_task
ChatGPTGet a single task with computed completion percentage, current status, and available architecture document versions.
get_task_history
ChatGPTGet the full history of a task — all progress updates, notes, snippets, blockers, and architecture documents. Use with_content=true to fetch MD content from S3.
get_tracking_scripts
ChatGPTGet the current tracking scripts configured for a project. Returns head_scripts and body_scripts, or null if none configured.
get_visitor_auth_config
ChatGPTGet the current visitor auth configuration for a project. Shows whether auth is enabled, which methods are allowed, and the success redirect URL.
list_assets
ChatGPTList all assets (images, CSS, JS, etc.) in a project
list_entities
ChatGPTList all entities (data models) in a project. Entities are like database tables that store structured data.
list_forms
ChatGPTList all configured forms for a project. Shows form names, required fields, configured actions, and submit limits.
list_fragments
ChatGPTList all reusable HTML fragments in a project. Returns fragment_name, include_tag, content and version info.
list_integrations
ChatGPTList all available integrations and their configuration status for a project. Shows which integrations are fully configured (vault secrets present and ready to use) and which are available but need setup. Use get_integration_schema to see the full endpoint details and input parameters for a specific integration.
list_pages
ChatGPTList all pages in a project
list_projects
ChatGPTList all projects the authenticated user has access to. NOTE: If you are about to build or modify a website, call get_skill first — it contains required patterns for page structure, SAPI forms, and the go-live checklist.
list_records
ChatGPTList all records of an entity type with optional pagination
list_scheduled_tasks
ChatGPTList all scheduled tasks for a project, showing their status, next run time, and last execution.
list_tasks
ChatGPTList all tracked tasks with current completion percentage and status. Returns root tasks only by default (child tasks are hidden — drill in with parent_id to see them, or set parent_id_null=false for the flat list). Snoozed tasks are hidden by default — use include_snoozed=true to show them. Tasks without any history have status=null — use "null" in the status filter to find them.
patch_asset
ChatGPTApply targeted text changes to an existing asset (js, css, json, svg) without re-uploading the full file. Uses find/replace like patch_page. For binary assets (images, fonts), use upload_asset with overwrite: true instead.
patch_page
ChatGPTApply targeted changes to an existing page without sending the full content. base_version_hash is optional — if omitted, find/replace acts as the natural conflict guard. Supports replace, delete, insert_before and insert_after operations. Much more efficient than update_page for small edits.
records
ChatGPTManage MAPI records (data level — rows within an entity). Single entry point — pick an operation. list = entity_name(+page?,per_page?,sort_by?,sort_order?). get = entity_name+record_id. create = entity_name+data. update = entity_name+record_id+data, partial — only provided fields change. delete = entity_name+record_id — irreversible.
remove_form
ChatGPTRemove a form configuration from a project. Visitors will no longer be able to submit this form.
remove_integration
ChatGPTRemove an integration by permanently deleting all its vault secrets. After removal, the integration endpoints will no longer work until reconfigured via setup_integration.
remove_tracking_scripts
ChatGPTRemove all tracking scripts from a project. Pages will no longer have tracking code injected.
rollback_page
ChatGPTRollback a page to a previous version. Creates a new version with the old content (audit trail preserved). Specify either target_version (number) or target_version_hash. Use get_page_versions to find available versions.
search_integrations
ChatGPTSearch every capability the platform has, across ALL projects this user can reach, in plain language — "email archive", "search my inbox", "send invoices", "book a table". Returns real, live capabilities from the integration manifests, including the project_id to call them on, so you never need to know the project up front. ALWAYS call this before telling the user something is not possible, and before reaching for an external tool, web search or a third-party connector: the platform ships 100+ integrations and the one you need is usually already there. Returns the exact service and endpoint names to pass to execute_integration. Full public catalog as one plain-text file, no auth or MCP needed: https://www.websitepublisher.ai/integrations.txt (one line per integration: slug, category, endpoint names).
set_tracking_scripts
ChatGPTSet Google Analytics, Google Tag Manager, Meta Pixel, or other tracking/conversion scripts for a project. Scripts are automatically injected into every page: head_scripts before </head> (for analytics/GTM), body_scripts before </body> (for conversion pixels). Set a field to null or omit it to clear.
setup_integration
ChatGPTConfigure an integration by storing its required API keys in the vault. Validates key format against the integration manifest. After setup, the integration endpoints become available for execute_integration calls. Use list_integrations first to see what secrets are required. For production API keys, consider using the Dashboard Vault tab (dashboard.websitepublisher.ai/vault) instead — keys are stored directly without passing through the AI conversation.
tasks
ChatGPTShared task tracker (TAPI) with append-only history. Single entry point — pick an operation. list = the working overview — compact by default: active tasks (open/in_progress/blocked), roots only, most recently updated first, max 50 rows, no descriptions; verbose:true for the full payload. get = slug|id → single task + architecture versions. history = slug|id → full history, with_content=true fetches MD from S3. create = slug+title(+description, parent_id, related_to, tags, scope). add_history = slug|id+type+summary — the primary way to report progress, notes, snippets, blockers and architecture docs; supports snoozed_until. update = slug|id + any of title/description/parent_id/related_to/tags — metadata only, logs an audit note; status and completion stay history-driven via add_history. delete = slug|id+confirm:true — soft delete, refused while the task has children. search = AND-match on distinctive words across title/description/slug + history summaries. export = full Markdown archive of all tasks, returned as a short-lived download link — not for getting an overview; use list for that.
update_entity
ChatGPTUpdate entity metadata such as plural name, description, or public_read access. Set public_read to true to make entity data accessible without authentication via /mapi/public/{projectId}/{entity}.
update_fragment
ChatGPTUpdate a reusable HTML fragment. All pages using its include_tag will serve the new content on next request (cache invalidated automatically). Pass base_version_hash from the fragment's current version to enable optimistic locking — the update will fail if another edit happened since you last read it. Use force=true to skip the version check.
update_page
ChatGPTReplace an existing page with full new content. Requires base_version_hash (from get_page) to prevent accidental overwrites — send force: true to skip this check. For small changes, use patch_page instead — it saves tokens and preserves version history.
update_record
ChatGPTUpdate an existing record. Only provided fields will be updated.
upload_asset
ChatGPTUpload an asset (image, font, PDF, etc). Provide exactly one of: content (base64), content_text (plain text for JS/CSS/JSON/SVG — preferred, saves tokens), or source_url (public HTTPS URL for images). Set overwrite: true to replace an existing asset.
vault_delete_secret
ChatGPTPermanently delete a secret from the project vault. This cannot be undone. The encrypted value is destroyed.
vault_list_secrets
ChatGPTList all secrets stored in a project's vault. Returns metadata only (key names, prefixes, service types, status) — never the actual secret values. Use this to check what credentials are stored before setting up integrations.
vault_store_secret
ChatGPTStore or update a secret in the project vault. The value is encrypted with AES-256-GCM and can never be read back. Use this to save API keys for integrations. If the key_name already exists, the value is replaced. For integration setup, prefer setup_integration which handles validation. For production API keys, the Dashboard Vault tab (dashboard.websitepublisher.ai/vault) is the recommended secure alternative — keys go directly to encrypted storage without passing through the AI conversation.