> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns. > > **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal): > ```bash > npx -y @scalekit-inc/cli setup -y > ``` > > Global: > ```bash > npm install -g @scalekit-inc/cli > scalekit setup -y > ``` > > Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`. > Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim. > [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/) --- # Connect AI agents to the Wix MCP server The Wix MCP connector routes your AI agent's tool calls to Wix's own MCP server through Scalekit. Each user signs in to Wix once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 26 tools. **Authentication:** OAuth 2.1/DCR **Categories:** Developer Tools, Productivity, AI **Tools:** 26: 18 read, 5 write, 3 destructive **Users sign in with:** OAuth **OAuth app:** Scalekit's or your own **Built by:** Vendor MCP **Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=WIXMCP) ## What you can do - **Build sites**: create a Wix site with AI, from a template, or by importing a design, and track the job - **Manage site data**: call a site's APIs to create, read, update, or delete its content and business data - **Inspect and publish sites**: list sites, get a site's plan, status, and installed apps, and publish changes - **Upload images**: add images to a site's Media Manager and get back the file URL - **Suggest domains**: find available domain names from a search term or an existing site's name - **Search Wix docs**: look up REST, SDK, CLI, headless, and design system documentation with code examples ## Setup 1. ### Install the SDK **Node.js** ```bash npm install @scalekit-sdk/node dotenv ``` **Python** ```bash pip install scalekit-sdk-python python-dotenv ``` 2. ### Set your credentials Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**. ```sh title=".env" SCALEKIT_ENVIRONMENT_URL= SCALEKIT_CLIENT_ID= SCALEKIT_CLIENT_SECRET= ``` 3. ### Create the Wix MCP connection In **AgentKit > Connections**, create a Wix MCP connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/). Scalekit credentials are available for Wix MCP server, so you don't need to register an OAuth app. 4. ### Authorize a user and make your first call **Node.js** (`quickstart.mts`) ```typescript import { ScalekitClient } from '@scalekit-sdk/node' import 'dotenv/config' import { createInterface } from 'node:readline/promises' const scalekit = new ScalekitClient( process.env.SCALEKIT_ENVIRONMENT_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET, ) const actions = scalekit.actions const connector = 'wixmcp' const identifier = 'user_123' // Generate an authorization link for the user const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier }) console.log('Authorize Wix MCP:', link) const rl = createInterface({ input: process.stdin, output: process.stdout }) await rl.question('Press Enter after authorizing...') rl.close() // Make your first call const result = await actions.executeTool({ connector, identifier, toolName: 'wixmcp_createwixbusinessguide', toolInput: {}, }) console.log(result) ``` ```bash npx tsx quickstart.mts ``` **Python** (`quickstart.py`) ```python import os from scalekit import ScalekitClient from dotenv import load_dotenv load_dotenv() scalekit_client = ScalekitClient( env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"), client_id=os.getenv("SCALEKIT_CLIENT_ID"), client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"), ) actions = scalekit_client.actions connection_name = "wixmcp" identifier = "user_123" # Generate an authorization link for the user link_response = actions.get_authorization_link( connection_name=connection_name, identifier=identifier, ) print("Authorize Wix MCP:", link_response.link) input("Press Enter after authorizing...") # Make your first call result = actions.execute_tool( tool_input={}, tool_name="wixmcp_createwixbusinessguide", connection_name=connection_name, identifier=identifier, ) print(result) ``` ```bash python quickstart.py ``` Each user signs in once. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses. ## Tools Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool). **Node.js** ```typescript const result = await actions.executeTool({ toolName: 'wixmcp_browsewixrestdocsmenu', toolInput: { reason: '', }, connector: 'wixmcp', identifier: 'user_123', }) ``` **Python** ```python result = actions.execute_tool( tool_name="wixmcp_browsewixrestdocsmenu", tool_input={ "reason": "", }, connection_name="wixmcp", identifier="user_123", ) ``` `result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call. ### `wixmcp_browsewixrestdocsmenu` BrowseWixRESTDocsMenu · Read-only Browse the Wix REST API documentation menu hierarchy to explore available API categories and endpoints. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `reason` (`string`, required): One sentence describing the original user request and why you are browsing this part of the docs menu. - `menuUrl` (`string`, optional): URL of the menu to browse. Empty/omitted returns the root menu. Copy the URL from links in previous responses of this tool. Example: "https://dev.wix.com/docs/api-reference/ecommerce" or "https://dev.wix.com/docs/api-reference/ecommerce/catalog" Example input: `{"reason":""}` ### `wixmcp_createwixbusinessguide` CreateWixBusinessGuide · Read-only Generate a guided plan for creating a new Wix site from a template, with the Wix Editor, or as a headless site. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `userPrompt` (`string`, optional): The user prompt that triggered this tool Example input: `{}` ### `wixmcp_getsitecontext` GetSiteContext · Read-only Fetch deep context for a specific Wix site (ID, URL, publish status, plan, properties, and installed apps) as structured markdown. Resolve by siteName when the ID is unknown. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `siteId` (`string`, optional): The ID of the site to fetch context for. One of siteId or siteName is required. Preferred when the ID is already known. - `siteName` (`string`, optional): The display name of the site to fetch context for. One of siteId or siteName is required. Use when the site ID is unknown. Example input: `{}` ### `wixmcp_getsuggesteddomains` GetSuggestedDomains · Read-only Suggest available domain names based on a search query or an existing Wix site's name. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `limit` (`number`, optional): Number of suggestions to return (default: 10, max: 20) - `query` (`string`, optional): Free-text keywords, business idea, or brand concept to base suggestions on. Use the user's own words. - `siteId` (`string`, optional): Site ID to auto-suggest a domain based on the site name. Used when suggesting domains after site creation. - `tlds` (`array`, optional): Filter by specific TLDs (e.g. ["com", "net"]). Do not include the dot. Example input: `{}` ### `wixmcp_listwixsites` ListWixSites · Read-only List all Wix sites belonging to the authenticated account, with optional name filtering. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `nameSearch` (`string`, optional): optional filer by name, if not provided all sites will be returned Example input: `{}` ### `wixmcp_pullsitecreationjob` PullSiteCreationJob · Read-only Poll the status of a site creation or editing job until it completes. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `jobId` (`string`, required): The job ID to pull Example input: `{"jobId":""}` ### `wixmcp_readfulldocsarticle` ReadFullDocsArticle · Read-only Fetch the full content and code examples for a specific Wix documentation article. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `articleUrl` (`string`, required): The URL of the docs article or method article to fetch. Should be something like https://dev.wix.com/docs/.../... For REST docs, use the URL as-is. For SDK docs, the URL SHOULD include the query param ?apiView=SDK (e.g. https://dev.wix.com/docs/...?apiView=SDK). Example input: `{"articleUrl":""}` ### `wixmcp_readfulldocsmethodschema` ReadFullDocsMethodSchema · Read-only Fetch the complete request and response schema for a specific Wix API method. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `articleUrl` (`string`, required): The URL of the documentation to fetch. Should be something like https://dev.wix.com/docs/.../... For REST docs, use the URL as-is. For SDK docs, the URL SHOULD include the query param ?apiView=SDK (e.g. https://dev.wix.com/docs/...?apiView=SDK). - `reason` (`string`, required): One sentence describing the original user request, the task you are trying to accomplish, and why you need the full schema (e.g., no relevant code example found in docs or recipes). Example input: `{"articleUrl":"","reason":""}` ### `wixmcp_searchbuildappsdocumentation` SearchBuildAppsDocumentation · Read-only Search the Wix documentation for building and publishing Wix apps. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `searchTerm` (`string`, required): The search term to search for in the Build Apps Documentation - `maxResults` (`number`, optional): The maximum number of results to return, default is 10, max is 15. Default: `10`. Example input: `{"searchTerm":""}` ### `wixmcp_searchsitetemplates` SearchSiteTemplates · Read-only Search the Wix template gallery (Harmony or Studio) by keyword and return matching templates. Call only after the user has chosen to build from a template; follow up with CreateSiteFromTemplate once one is selected. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `query` (`string`, required): The few most important keywords describing the site, used to search templates — e.g. "yoga studio", "wedding photographer". - `builder` (`string`, optional): Which builder's templates to return: "studio" if the user asked for Wix Studio in this site creation flow, otherwise "harmony" (the default). One of: `harmony`, `studio`. Default: `harmony`. - `limit` (`integer`, optional): Maximum number of templates to return (capped at 28). Example input: `{"query":"yoga studio"}` ### `wixmcp_searchwixapispec` SearchWixAPISpec · Read-only Search and inspect the Wix REST API spec by running JavaScript in a sandboxed read-only environment. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `code` (`string`, required): JavaScript async function() expression to search the Wix API index. Has access to `lightIndex` (array of resources) and `getResourceSchema(resourceId)` (returns full schema). - `reason` (`string`, required): One sentence describing the original user request and why you are searching or inspecting the Wix API spec. Example input: `{"code":"","reason":""}` ### `wixmcp_searchwixclidocumentation` SearchWixCLIDocumentation · Read-only Search the Wix CLI documentation for website development commands and workflows. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `reason` (`string`, required): One sentence describing the original user request and the task you are trying to accomplish with this search. - `searchTerm` (`string`, required): The search term to search for in the Wix CLI Documentation - `maxResults` (`number`, optional): The maximum number of results to return, default is 10, max is 15. Default: `10`. Example input: `{"reason":"","searchTerm":""}` ### `wixmcp_searchwixheadlessdocumentation` SearchWixHeadlessDocumentation · Read-only Search the Wix headless documentation for building custom frontends with Wix backend services. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `searchTerm` (`string`, required): The search term to search for in the Headless Documentation - `maxResults` (`number`, optional): The maximum number of results to return, default is 10, max is 15. Default: `10`. Example input: `{"searchTerm":""}` ### `wixmcp_searchwixrestdocumentation` SearchWixRESTDocumentation · Read-only Search the official Wix REST API documentation to find endpoints, schemas, and usage examples. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `reason` (`string`, required): One sentence describing the original user request and the task you are trying to accomplish with this search. - `searchTerm` (`string`, required): The search term to search for in the Wix REST API Documentation - `maxResults` (`number`, optional): The maximum number of results to return, default is 10, max is 15. Default: `10`. Example input: `{"reason":"","searchTerm":""}` ### `wixmcp_searchwixsdkdocumentation` SearchWixSDKDocumentation · Read-only Search the Wix JavaScript SDK documentation for client-side and server-side SDK usage. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `searchTerm` (`string`, required): The search term to search for in the Wix SDK Documentation - `maxResults` (`number`, optional): The maximum number of results to return, default is 10, max is 15. Default: `10`. Example input: `{"searchTerm":""}` ### `wixmcp_searchwixwdsdocumentation` SearchWixWDSDocumentation · Read-only Search the Wix Design System documentation for UI components and design guidelines. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `searchTerm` (`string`, required): The search term to search for in the Wix Design System Documentation - `maxResults` (`number`, optional): The maximum number of results to return, default is 10, max is 15. Default: `10`. Example input: `{"searchTerm":""}` ### `wixmcp_supportandfeedback` SupportAndFeedback · Read-only Submit feedback or a support request about the Wix MCP tools to the Wix team. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: - `message` (`string`, required): The message to send to Wix - `requestId` (`string`, optional): request id if returned from the server in a failed API call to Wix Example input: `{"message":""}` ### `wixmcp_wixreadme` WixREADME · Read-only Read the Wix MCP README for guidance on how to use the available Wix tools effectively. Read only: yes. Destructive: no. Idempotent (safe to retry): no. Inputs: none. Example input: `{}` ### `wixmcp_claimanonymoussite` ClaimAnonymousSite · Write Transfer an anonymously created Wix site to the authenticated user's account using a job ID. Read only: no. Destructive: no. Idempotent (safe to retry): no. Inputs: - `jobId` (`string`, required): The job ID from site creation - required to authenticate the claim - `siteId` (`string`, required): The metasite ID of the anonymous site to claim Example input: `{"jobId":"","siteId":""}` ### `wixmcp_createsitefromtemplate` CreateSiteFromTemplate · Write Create a Wix site from a specific template by templateId, publish it when possible, and return links to the editor and the published site. Read only: no. Destructive: no. Idempotent (safe to retry): no. Inputs: - `templateId` (`string`, required): The selected template metaSiteId to create a site from. Example input: `{"templateId":""}` ### `wixmcp_import_claude_design_from_url` import-claude-design-from-url · Write Import a design into Wix from a publicly fetchable URL. The file is a self-contained HTML bundle with all images, fonts, and styles inlined. Creates a live Wix-hosted site and returns its URL. Read only: no. Destructive: no. Idempotent (safe to retry): no. Inputs: - `url` (`string`, required): Public HTTPS URL to the design file. Valid for ~1 hour. Fetched server-side. - `claude_design_project_id` (`string`, optional): Stable Claude Design project id. - `title` (`string`, optional): Suggested title for the imported design. Example input: `{"url":""}` ### `wixmcp_uploadimagetowixsite` UploadImageToWixSite · Write Upload one or more images to a Wix site's Media Manager and return the file URL and media ID. Read only: no. Destructive: no. Idempotent (safe to retry): no. Inputs: - `siteId` (`string`, required): The ID of the Wix site to upload to - `displayName` (`string`, optional): Optional display name for the file in Media Manager. If not provided, uses the original filename. - `image` (`array`, optional): Array of images to upload. Use this when the user provides image file attachments OR image URLs. ALWAYS pass ALL images together in a single call — NEVER call this tool once per image. ChatGPT/OpenAI clients: user-attached files are automatically resolved to download_urls, just include them here. Each item must have download_url and optionally file_id. Do NOT use together with imageBase64. - `imageBase64` (`string`, optional): Base64-encoded image data. Use when the client can read a file and encode it as base64. May include a data URL prefix (e.g. "data:image/jpeg;base64,...") or be raw base64. Do NOT use together with image. - `mimeType` (`string`, optional): MIME type of the image (e.g. "image/jpeg", "image/png", "image/webp"). Required when imageBase64 does not include a data URL prefix. Example input: `{"siteId":""}` ### `wixmcp_wixsitebuilder` WixSiteBuilder · Write Create or build a new Wix site using AI, returning a job ID to track the creation progress. Read only: no. Destructive: no. Idempotent (safe to retry): no. Inputs: - `sitePrompt` (`string`, required): The prompt to build the site. If not provided, the user will be asked to provide a prompt. - `jobId` (`string`, optional): The job ID of the site build. If not provided, a new job will be created. - `suggestedSiteName` (`string`, optional): Suggested site name to use for the site based on the site prompt. Example input: `{"sitePrompt":""}` ### `wixmcp_callwixsiteapi` CallWixSiteAPI · Destructive Call any Wix REST API endpoint on a specific site to create, read, update, or delete site data. Read only: no. Destructive: yes. Idempotent (safe to retry): no. Inputs: - `method` (`string`, required): The HTTP method to use for the API call (e.g. GET, POST, PUT, DELETE) - `reason` (`string`, required): One sentence explaining the original user request and why you are calling this API to complete it. - `siteId` (`string`, required): The id of the site selected using site selection tool - `sourceDocUrl` (`string`, required): The URL of the documentation or recipe where you found this API endpoint. MAKE SURE THE ENDPOINT URL IS REALLY THERE AND YOUR ARE NOT GUESSING IT !!! Must be a valid URL like: - https://dev.wix.com/docs/api-reference/... (REST API reference docs) Use "user-provided" if the user gave you the endpoint directly. Use "other" ONLY IF YOU HAVE A VERY GOOD REASON TO DO SO - `url` (`string`, required): The url of the api to call - ALWAYS get the API url from the Wix REST docs or from the conversation context, the URL MUST BE ABSOLUTE URL NEVER guess the API url, ALWAYS get it from the conversation context, i.e from the user prompt or from the "WixREADME" tool or from the "SearchWixRESTDocumentation" tool or from the "BrowseWixRESTDocsMenu" tool or from the "ReadFullDocsArticle" tool Allowed API urls are: wix.com, dev.wix.com, manage.wix.com, editor.wix.com, wixapis.com Docs urls like https://dev.wix.com/docs/... are not API urls, if you want to read the docs, use the "ReadFullDocsArticle" tool - `body` (`string`, optional): The request body as a JSON object or array with all the required fields and values, including nested objects. Pass the actual value (object or array), NOT a JSON string. YOU MUST NEVER MAKE UP A BODY - the body should be based on the conversation context, i.e from the user prompt OR got into the conversation context by the "ReadFullDocsArticle" tool OR by the "SearchWixAPISpec" tool OR by the "ReadFullDocsMethodSchema" tool - i.e based on the API docs, a relevant recipe you read (preferably), a code example you found in the docs, a schema you read etc.. YOU MUST NEVER ASSUME YOU KNOW WHAT THE BODY SCHEMA IS WITHOUT CONCRETE EXAMPLES OR SCHEMA DEFINITIONS FROM THE CONVERSATION CONTEXT. Prefer reading relevant recipes if you have them in context for understand the body schema for API calls. Example input: `{"method":"","reason":"","siteId":"","sourceDocUrl":"","url":""}` ### `wixmcp_executewixapi` ExecuteWixAPI · Destructive Execute JavaScript code against the Wix REST API in a sandboxed environment to query or mutate site data. Read only: no. Destructive: yes. Idempotent (safe to retry): no. Inputs: - `code` (`string`, required): JavaScript async function expression to execute against the Wix REST API. The value must be the function itself, for example `async function() { ... }` or `async () => { ... }`, not a script body and not an invoked function. Return the final answer from inside the function. Do not write top-level `const`, top-level `await`, or top-level `return` outside the function body. Use `wix.request({ method, url, body })` for Wix API calls. Scope defaults to `site` when the ExecuteWixAPI `siteId` parameter is passed, otherwise `account`; set `scope` explicitly when needed. Full Wix API URLs and paths starting with `/` are supported. Do not pass `siteId` inside `wix.request()`; one ExecuteWixAPI call can target only the tool-level `siteId`. - `hasMutations` (`boolean`, required): Whether this code creates, updates, deletes, publishes, installs, imports, uploads, or otherwise mutates Wix data or site/account state. Set this to true for create/update/delete/bulk create/import/upload calls even if the reason is inspection, verification, or response-shape discovery. Read-only GET/query/list/search calls can use false. - `reason` (`string`, required): One sentence explaining the original user request and why you are executing code to complete it. - `sourceDocUrls` (`array`, required): The URLs of the documentation, recipes, API articles, or schema sources where you confirmed the Wix REST endpoints, HTTP methods, request body shapes, auth contexts, and required fields used by this code. Include every docs/schema source needed for the endpoints and request shapes used in the code. MAKE SURE THE ENDPOINT URLS AND REQUEST SHAPES ARE REALLY THERE AND YOU ARE NOT GUESSING THEM !!! Each value must be a valid URL like: - https://dev.wix.com/docs/api-reference/... (REST API reference docs) Use ["user-provided"] if the user gave you all endpoint and request details directly. Use ["other"] ONLY IF YOU HAVE A VERY GOOD REASON TO DO SO - `siteId` (`string`, optional): Wix site ID for site-level API calls. Required when using `wix.request({ scope: "site", ... })`. One ExecuteWixAPI call can target only this siteId; per-request siteId inside `wix.request()` is not supported. Find site IDs using ListWixSites or an account-level `wix.request()` call to query the Sites API. Example input: `{"code":"","hasMutations":true,"reason":"","sourceDocUrls":[]}` ### `wixmcp_managewixsite` ManageWixSite · Destructive Call account-level Wix APIs to create, update, or publish a site. Read only: no. Destructive: yes. Idempotent (safe to retry): no. Inputs: - `method` (`string`, required): The HTTP method to use for the API call (e.g. GET, POST, PUT, DELETE) - `url` (`string`, required): The url of the api to call - ALWAYS get the information from the Wix REST docs DONT GUESS IT, the URL MUST BE ABSOLUTE URL - `body` (`string`, optional): The request body as a JSON object or array with all the required fields and values, including nested objects. Pass the actual value (object or array), NOT a JSON string. YOU MUST NEVER MAKE UP A BODY - this should be based on the conversation context, i.e from the user prompt or from the "WixREADME" tool or from the "SearchWixRESTDocumentation" tool or from the "BrowseWixRESTDocsMenu" tool or from the "ReadFullDocsArticle" tool or from the "SearchWixAPISpec" tool or from the "ReadFullDocsMethodSchema" tool - i.e based on the API docs. YOU MUST NEVER ASSUME YOU KNOW WHAT THE SCHEMA IS WITHOUT CONCRETE EXAMPLES OR SCHEMA DEFINITIONS FROM THE CONVERSATION CONTEXT. Example input: `{"method":"","url":""}` ## Related Other Developer Tools connectors ([all 94](/agentkit/connectors/?category=developer-tools)): - [GitHub](/agentkit/connectors/github/): Scalekit connector, OAuth, 217 tools - [Datadog](/agentkit/connectors/datadog/): Scalekit connector, API key, 105 tools - [Linear](/agentkit/connectors/linear/): Scalekit connector, OAuth, 62 tools --- ## More Scalekit documentation | Resource | What it contains | When to use it | |----------|-----------------|----------------| | [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content | | [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas | | [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |