### Install Dependencies and Start App Source: https://github.com/botpress/docs/blob/master/webchat/integrations/react-native.mdx These commands are used to install project dependencies and start the React Native development server. ```bash npm install npx expo start ``` -------------------------------- ### Install Dependencies and Build Integration Source: https://github.com/botpress/docs/blob/master/integrations/sdk/integration/getting-started.mdx Navigate to your integration directory, install its dependencies, and build the project. ```bash cd ./my-integration npm i bp build ``` -------------------------------- ### Start Local Development Server Source: https://github.com/botpress/docs/blob/master/README.md Start a local Mintlify development server to preview the documentation site. ```bash mint dev ``` -------------------------------- ### Install Dependencies and Build Bot Source: https://github.com/botpress/docs/blob/master/integrations/sdk/bots-as-code.mdx Navigate to the bot directory, install npm dependencies, and build the bot project. ```bash cd ./my-bot npm i bp build ``` -------------------------------- ### Install All Skills Source: https://github.com/botpress/docs/blob/master/adk/ai-native/skills.mdx Installs all available skills for the specified AI assistants. Use `bunx` if your project uses `bun.lockb`. ```bash npx skills add botpress/skills -s '*' -a codex claude-code -y ``` -------------------------------- ### List Tables using TypeScript Client Source: https://github.com/botpress/docs/blob/master/api-reference/tables-api/getting-started.mdx This example shows how to list tables using the official Botpress TypeScript client. It requires installing the client package and configuring your API token and bot ID. ```APIDOC ## listTables ### Description Lists all tables associated with the bot using the official TypeScript client. ### Method `client.listTables({})` ### Parameters #### Path Parameters None #### Query Parameters None #### Request Body - **options** (object) - Optional - Configuration options for the method. - **where** (object) - Optional - Filters for the tables. - **limit** (number) - Optional - Maximum number of tables to return. - **skip** (number) - Optional - Number of tables to skip. ### Request Example ```ts import dotenv from 'dotenv' import { Client } from '@botpress/client' dotenv.config() const main = async () => { const token = process.env.TOKEN const botId = process.env.BOT_ID const client = new Client({ token, botId, }) const response = await client.listTables({}) console.log(response.tables) } void main() ``` ### Response #### Success Response (200) - **tables** (array) - A list of table objects. #### Response Example ```json { "tables": [ { "id": "table_id_1", "name": "users", "createdAt": "2023-10-27T10:00:00Z", "updatedAt": "2023-10-27T10:00:00Z" }, { "id": "table_id_2", "name": "products", "createdAt": "2023-10-27T10:05:00Z", "updatedAt": "2023-10-27T10:05:00Z" } ] } ``` ``` -------------------------------- ### Install react-native-webview with npm Source: https://github.com/botpress/docs/blob/master/webchat/integrations/react-native.mdx Install the react-native-webview package using npm. ```bash npm install react-native-webview ``` -------------------------------- ### Start development server Source: https://github.com/botpress/docs/blob/master/adk/cli-reference.mdx Start the development server with hot reloading. You can specify custom ports for the bot server and the dev console. ```bash adk dev adk dev --port 3000 --port-console 3001 ``` -------------------------------- ### Start Development Server Source: https://github.com/botpress/docs/blob/master/adk/quickstart.mdx Builds the agent, deploys it to a development bot, and starts a local development server with hot reloading. Access the dev console at http://localhost:3001/. ```bash adk dev ``` -------------------------------- ### Install react-native-webview with yarn Source: https://github.com/botpress/docs/blob/master/webchat/integrations/react-native.mdx Install the react-native-webview package using yarn. ```bash yarn add react-native-webview ``` -------------------------------- ### Install Single Skill Source: https://github.com/botpress/docs/blob/master/adk/ai-native/skills.mdx Installs a specific skill, such as the core ADK framework skill. ```bash npx skills add botpress/skills --skill adk ``` -------------------------------- ### Install Botpress CLI Source: https://github.com/botpress/docs/blob/master/integrations/sdk/bots-as-code.mdx Install the Botpress CLI globally using npm, pnpm, or yarn. ```bash npm install -g @botpress/cli ``` ```bash pnpm install -g @botpress/cli ``` ```bash yarn add -g @botpress/cli ``` -------------------------------- ### List installed or available integrations Source: https://github.com/botpress/docs/blob/master/adk/cli-reference.mdx List integrations installed in your project, or all available integrations on the Botpress Hub. You can limit the number of results. ```bash adk list adk list --available ``` -------------------------------- ### Install react-native-webview with pnpm Source: https://github.com/botpress/docs/blob/master/webchat/integrations/react-native.mdx Install the react-native-webview package using pnpm. ```bash pnpm add react-native-webview ``` -------------------------------- ### Example Action Prompt Source: https://github.com/botpress/docs/blob/master/studio/concepts/actions.mdx This is an example prompt used to generate an Action. AI will create code based on this description. ```text Use the `fetchApiData` Action when you need data from an external API. ``` -------------------------------- ### Install react-native-webview for Expo Source: https://github.com/botpress/docs/blob/master/webchat/integrations/react-native.mdx Install the react-native-webview package for Expo projects using npx. ```bash npx expo install react-native-webview ``` -------------------------------- ### Install Dependencies with pnpm Source: https://github.com/botpress/docs/blob/master/README.md Install project dependencies using the pnpm package manager. ```bash pnpm install ``` -------------------------------- ### Install Botpress Client Source: https://github.com/botpress/docs/blob/master/api-reference/admin-api/getting-started.mdx Install the Botpress client package using npm. This is required for programmatic interaction with the Admin API. ```bash npm install @botpress/client ``` -------------------------------- ### Install Botpress TypeScript Client Source: https://github.com/botpress/docs/blob/master/api-reference/runtime-api/getting-started.mdx Install the official Botpress TypeScript client using npm, pnpm, or yarn. ```bash npm install @botpress/client ``` ```bash pnpm install @botpress/client ``` ```bash yarn add @botpress/client ``` -------------------------------- ### Manual Webchat Initialization Example Source: https://github.com/botpress/docs/blob/master/webchat/integrations/wix.mdx An example of the Webchat initialization script content. This is what you should copy after opening the URL provided by GetInitScript to embed the bot in an HTML div. ```javascript import ManualInit from "/snippets/webchat/manual-init.mdx"; ``` -------------------------------- ### Install ADK CLI on Windows Source: https://github.com/botpress/docs/blob/master/adk/quickstart-ai-assistant.mdx Installs the ADK CLI using a PowerShell command. This is the command for Windows systems. ```powershell powershell -c "irm https://github.com/botpress/adk/releases/latest/download/install.ps1 | iex" ``` -------------------------------- ### Install Botpress CLI with npm Source: https://github.com/botpress/docs/blob/master/integrations/sdk/installation.mdx Install the Botpress CLI globally using npm. This command makes the Botpress CLI available system-wide. ```bash npm install -g @botpress/cli ``` -------------------------------- ### Install Botpress CLI with pnpm Source: https://github.com/botpress/docs/blob/master/integrations/sdk/installation.mdx Install the Botpress CLI globally using pnpm. This command makes the Botpress CLI available system-wide. ```bash pnpm install -g @botpress/cli ``` -------------------------------- ### Verify Botpress CLI Installation Source: https://github.com/botpress/docs/blob/master/integrations/sdk/installation.mdx Check if the Botpress CLI was installed successfully by running the help command. This confirms the CLI is accessible and functional. ```bash bp --help ``` -------------------------------- ### Starting MCP Server with ADK CLI Source: https://github.com/botpress/docs/blob/master/adk/cli-reference.mdx Start the MCP server so tools like Claude Code, Cursor, or VS Code can talk to your running dev server. ```bash adk mcp adk mcp --port 3001 ``` -------------------------------- ### Install Botpress CLI with yarn Source: https://github.com/botpress/docs/blob/master/integrations/sdk/installation.mdx Install the Botpress CLI globally using yarn. This command makes the Botpress CLI available system-wide. ```bash yarn add -g @botpress/cli ``` -------------------------------- ### Start a Workflow Programmatically Source: https://github.com/botpress/docs/blob/master/adk/workflows/create.mdx Initiate a workflow instance from your code using its imported class and the 'start' method, passing any required input. ```typescript import ProcessOrderWorkflow from "../workflows/processOrder" const instance = await ProcessOrderWorkflow.start({ orderId: "12345" }) console.log("Started workflow:", instance.id) ``` -------------------------------- ### Start Crawler Run Source: https://github.com/botpress/docs/blob/master/snippets/integrations/cards/plus/plus-apify.mdx Start a crawler run asynchronously. Use with webhooks for production crawling. You can provide individual parameters or use rawInputJsonOverride for full control. ```APIDOC ## Start Crawler Run ### Description Start a crawler run asynchronously. Use with webhooks for production crawling. You can either use individual parameters for simple cases, or provide rawInputJsonOverride for full control. ### Method POST ### Endpoint /v1/cards/apify/runs/start ### Parameters #### Request Body - **startUrls** (array) - Required - URLs to start crawling from - **excludeUrlGlobs** (array) - Optional - URL patterns to exclude from crawling - **includeUrlGlobs** (array) - Optional - URL patterns to include in crawling - **maxCrawlPages** (number) - Required - Maximum number of pages to crawl - **saveMarkdown** (boolean) - Required - Save content as Markdown format - **htmlTransformer** (enum) - Required - HTML processing method. Available options: `readableTextIfPossible`, `readableText`, `extractus`, `none` - **removeElementsCssSelector** (string) - Optional - CSS selectors for elements to remove - **crawlerType** (enum) - Required - Browser type for crawling. Available options: `playwright:adaptive`, `playwright:firefox`, `cheerio`, `jsdom`, `playwright:chrome` - **expandClickableElements** (boolean) - Required - Expand clickable elements for better content extraction - **headers** (string) - Optional - Custom HTTP headers for authentication/requests - **rawInputJsonOverride** (string) - Optional - JSON string to override any crawler parameters. Please refer to https://console.apify.com/actors//input and select JSON format for the available parameters. - **kbId** (string) - Required - Knowledge Base ID to save the crawled content to ### Request Example { "startUrls": ["https://example.com"], "maxCrawlPages": 10, "saveMarkdown": true, "htmlTransformer": "readableText", "crawlerType": "playwright:chrome", "expandClickableElements": true, "kbId": "your_kb_id" } ### Response #### Success Response (200) - **success** (boolean) - Whether the operation completed successfully - **message** (string) - Status message describing the result - **data** (object) - Run details including run ID and current status - **runId** (string) - Required - **status** (string) - Required ### Response Example { "success": true, "message": "Crawler run started successfully", "data": { "runId": "new_run_id", "status": "RUNNING" } } ``` -------------------------------- ### Rewrite text Source: https://github.com/botpress/docs/blob/master/adk/zai/generate.mdx Transforms text based on instructions. Can use few-shot examples to guide the rewriting process. ```APIDOC ## Rewrite text ### Description Transforms text based on instructions. Can use few-shot examples to guide the rewriting process. ### Method `zai.rewrite(text: string, instructions: string, options?: { length: number, examples: Array<{input: string, output: string, instructions?: string}> })` ### Parameters #### Path Parameters None #### Query Parameters None #### Request Body None ### Parameters - **text** (string) - Required - The text to transform. - **instructions** (string) - Required - Instructions for rewriting the text. - **options.length** (number) - Optional - Max tokens to generate. - **options.examples** (Array<{input: string, output: string, instructions?: string}>) - Optional - Few-shot examples to guide the rewriting. ``` -------------------------------- ### Initialize a New Project Source: https://github.com/botpress/docs/blob/master/integrations/sdk/cli-reference.mdx Use `bp init` to start a new project. Specify the project type, name, and template as needed. ```bash bp init bp init --type bot --name my-bot bp init --type integration --template webhook-message ``` -------------------------------- ### Rewrite Text with zai.rewrite() Source: https://github.com/botpress/docs/blob/master/adk/zai/generate.mdx Use zai.rewrite() to transform text based on instructions. Optionally provide few-shot examples to guide the rewriting process. ```typescript const formal = await adk.zai.rewrite( "hey, the meeting is tmrw at 3", "Make this professional and formal" ) // "The meeting has been scheduled for tomorrow at 3:00 PM." ``` -------------------------------- ### Fetch Bot Analytics Data Source: https://github.com/botpress/docs/blob/master/studio/guides/advanced/exporting-data/exporting-compiled-bot-analytics-with-the-botpress-api.mdx Use this JavaScript snippet with Axios to make a GET request to the Botpress Cloud API for bot analytics. Ensure your personal access token is securely stored and accessed, for example, via environment variables. ```ts const requestConfig = { headers: { Authorization: `Bearer ${process.env.BOTPRESS_PERSONAL_ACCESS_TOKEN}`, }, } const getAnalytics = await axios.get(`https://api.botpress.cloud/v1/admin/${botId}/analytics`, requestConfig) ``` -------------------------------- ### Create and Upload File via HTTP Source: https://github.com/botpress/docs/blob/master/api-reference/files-api/how-tos/creating-files.mdx Use this method when you cannot install the Botpress Client package or are working with a different programming language. It requires two HTTP requests: one to create the empty file and another to upload its content. A third request may be needed to get the file URL. ```typescript const fileContent = 'Here goes the content of your file' const buffer = Buffer.from(fileContent) // Step 1: Create the file in Botpress Cloud. // Please note that specifying the file size (in raw bytes, not characters) is required when calling this endpoint. const result = await fetch('https://api.botpress.cloud/v1/files', { method: 'PUT', headers: { 'x-bot-id': 'YOUR_BOT_ID_GOES_HERE', 'Content-Type': 'application/json', Authorization: `Bearer ${process.env.BOTPRESS_PAT}`, }, body: JSON.stringify({ key: 'unique_file_name.txt', size: buffer.byteLength, }), }) const response = await result.json() // Step 2: Upload the file content to the unique upload URL provided for the created file. await fetch(response.file.uploadUrl, { method: 'PUT', body: buffer, }) // The variable below will contain the URL to download the file content uploaded above. If the file was // created with the 'public_content' access policy it will be a permanent URL that you can store long-term, // otherwise it will contain a temporary pre-signed URL that expires after a short period of time. // If you need to get a new URL, you can always use the `getFile` API endpoint. const downloadUrl = response.file.url ``` -------------------------------- ### Get User Profile Source: https://github.com/botpress/docs/blob/master/snippets/integrations/cards/botpress/slack.mdx Get information about a user. ```APIDOC ## Get User Profile ### Description Get information about a user. ### Input - **userId** (string) - Required - The ID of the user to retrieve information about ### Output - **firstName** (string) - The first name of the user - **lastName** (string) - The last name of the user - **email** (string) - The email of the user - **displayName** (string) - The display name of the user ``` -------------------------------- ### Build a Project Source: https://github.com/botpress/docs/blob/master/integrations/sdk/cli-reference.mdx Use `bp build` to generate typings and bundle your project. Control sourcemap generation and minification. ```bash bp build bp build --work-dir ./my-project --minify false ``` -------------------------------- ### Install Claude Code Plugin Source: https://github.com/botpress/docs/blob/master/adk/ai-native/skills.mdx Installs the skills as a plugin for Claude Code. This involves two steps: adding to the marketplace and then installing the specific skill. ```bash /plugin marketplace add botpress/skills ``` ```bash /plugin install adk@botpress-skills ``` -------------------------------- ### Get Website Logo Source: https://github.com/botpress/docs/blob/master/snippets/integrations/cards/botpress/browser.mdx Get the logo of the specified website. ```APIDOC ## POST /api/v1/browser/get-website-logo ### Description Get the logo of the specified website. ### Method POST ### Endpoint /api/v1/browser/get-website-logo ### Parameters #### Request Body - **input** (object) - Required - **domain** (string) - Required - The domain of the website to get the logo from (eg. "example.com") - **greyscale** (boolean) - Optional - Whether to return the logo in grayscale (black & white) (defaults to false) - **size** (enum) - Optional - Size of the logo to return (64, 128 or 256, 512 pixels) (defaults to "128"). Available options: `64`, `128`, `256`, `512` ### Response #### Success Response (200) - **output** (object) - Required - **logoUrl** (string) - Required - URL to the website logo ``` -------------------------------- ### Initialize a new agent project Source: https://github.com/botpress/docs/blob/master/adk/cli-reference.mdx Scaffold a new agent project. You can specify a name and a template, or list available templates. ```bash adk init my-agent adk init my-agent --template hello-world adk init --list-templates ``` -------------------------------- ### Create a Knowledge Base Source: https://github.com/botpress/docs/blob/master/adk/data/knowledge.mdx Define a knowledge base with a name, description, and data sources. Use `DataSource.Website.fromSitemap` to index website content. ```typescript import { Knowledge, DataSource } from "@botpress/runtime" export default new Knowledge({ name: "product-docs", description: "Product documentation and FAQ", sources: [ DataSource.Website.fromSitemap("https://docs.example.com/sitemap.xml"), ], }) ``` -------------------------------- ### Initialize a New Integration Source: https://github.com/botpress/docs/blob/master/integrations/sdk/integration/getting-started.mdx Create a new integration project using the Botpress CLI, specifying the type, name, and template. ```bash bp init --type "integration" --name "my-integration" --template "hello-world" ``` -------------------------------- ### Implementing the `startHitl` Action Source: https://github.com/botpress/docs/blob/master/integrations/sdk/interface/how-tos/implementing-hitl.mdx Implement the `startHitl` action to handle the creation of a HITL session. This snippet shows how to retrieve custom parameters passed via the `hitlSession` input and use them when interacting with an external service. ```typescript export default new bp.Integration({ actions: { async startHitl({ ctx, input, client }) { // Retrieve the extra parameter: const priority = input.hitlSession?.priority ?? 'normal' // Then use it to create the HITL session: const createdZendeskTicket = await zendeskClient .createTicket(ticketTitle, ticketBody, { priority, // <= pass the extra parameter to the external service }) }, }, }) ``` -------------------------------- ### Initialize New Bot Source: https://github.com/botpress/docs/blob/master/integrations/sdk/bots-as-code.mdx Create a new bot project with a specified type, name, and template using the Botpress CLI. ```bash bp init --type "bot" --name "my-bot" --template "empty" ``` -------------------------------- ### Initialize, Develop, and Deploy an ADK Agent Source: https://github.com/botpress/docs/blob/master/adk/introduction.mdx Scaffold a new agent project, run it locally with hot reloading, and deploy it to Botpress Cloud using the ADK CLI. ```bash adk init my-agent # Scaffold a project adk dev # Run locally with hot reload adk deploy # Ship to Botpress Cloud ``` -------------------------------- ### Implement startHitl Action for Zendesk Integration Source: https://github.com/botpress/docs/blob/master/integrations/sdk/interface/how-tos/implementing-hitl.mdx This TypeScript code demonstrates how to implement the `startHitl` action. It fetches a Botpress user, retrieves an external user ID from tags, creates a ticket in Zendesk, creates a Botpress conversation mapped to the Zendesk ticket, updates the Zendesk ticket with the conversation ID, and finally returns the Botpress conversation ID. ```typescript export default new bp.Integration({ actions: { async startHitl({ ctx, input, client }) { // Fetch the Botpress user that was passed in the input parameters: const { user } = await client.getUser({ id: input.userId, }) // From the user's tags, retrieve the external user's id: const zendeskAuthorId = user.tags.id if (!zendeskAuthorId) { throw new sdk.RuntimeError( `User ${user.id} isn't linked to a Zendesk user` ) } // Create a new ticket on Zendesk: const zendeskClient = getZendeskClient(ctx.configuration) const ticketTitle = input.title ?? 'Untitled Ticket' const ticketBody = 'A user created a support ticket' const createdZendeskTicket = await zendeskClient .createTicket(ticketTitle, ticketBody, { id: zendeskAuthorId, // <= map the ticket to the external user ID }) // Create a Botpress conversation and map it to the Zendesk ticket: const { conversation } = await client.getOrCreateConversation({ channel: 'hitl', tags: { id: createdZendeskTicket.id.toString(), // <= map to the ticket ID }, }) // Map the Zendesk ticket to the Botpress conversation: await zendeskClient.updateTicket(createdZendeskTicket.id, { external_id: conversation.id, // <= map to the Botpress conversation ID }) // Yield control back to the plugin and return the conversation ID: return { conversationId: conversation.id, // <= return the Botpress conversation ID } }, }, }) ``` -------------------------------- ### Update All Integrations in Bulk Source: https://github.com/botpress/docs/blob/master/README.md Fetch the most up-to-date information for all integrations at once. ```zsh pnpm run update-integrations --bulk ``` -------------------------------- ### Verify ADK Installation Source: https://github.com/botpress/docs/blob/master/adk/quickstart.mdx Checks if the ADK CLI has been installed correctly by displaying its current version. ```bash adk --version ``` -------------------------------- ### Install Webchat NPM Package Source: https://github.com/botpress/docs/blob/master/webchat/react-library/get-started.mdx Install the Webchat React library using your preferred package manager. ```bash npm install @botpress/webchat ``` ```bash yarn add @botpress/webchat ``` ```bash pnpm install @botpress/webchat ``` -------------------------------- ### Serve Project Locally Source: https://github.com/botpress/docs/blob/master/integrations/sdk/cli-reference.mdx Use `bp serve` to run your project locally. You can specify the port and environment secrets. ```bash bp serve bp serve --port 8080 --secrets SECRET1=value1 SECRET2=value2 ``` -------------------------------- ### Install Package CLI Command Source: https://github.com/botpress/docs/blob/master/integrations/sdk/cli-reference.mdx Use the `add` command to install packages like integrations or interfaces. You can specify the package name and version, or use flags like `--package-type` and `--use-dev`. ```bash bp add teams@0.2.0 ``` ```bash bp add llm --package-type interface ``` ```bash bp add knowledge --use-dev ``` -------------------------------- ### Initializing MCP Configuration with ADK CLI Source: https://github.com/botpress/docs/blob/master/adk/cli-reference.mdx Generate MCP configuration files for supported AI assistants. ```bash adk mcp:init --all adk mcp:init --tool claude-code adk mcp:init --tool vscode cursor ``` -------------------------------- ### Initialize New Agent Project Source: https://github.com/botpress/docs/blob/master/adk/quickstart.mdx Creates a new AI agent project named 'my-agent' using the ADK CLI. Follow the prompts to select a template, package manager, and link to a Botpress workspace. ```bash adk init my-agent ``` -------------------------------- ### List Tables using Botpress TypeScript Client Source: https://github.com/botpress/docs/blob/master/api-reference/tables-api/getting-started.mdx This TypeScript example demonstrates how to initialize the Botpress client and list all tables for a bot. It uses dotenv to load credentials from environment variables. ```typescript import dotenv from 'dotenv' import { Client } from '@botpress/client' dotenv.config() const main = async () => { const token = process.env.TOKEN const botId = process.env.BOT_ID const client = new Client({ token, botId, }) const response = await client.listTables({}) console.log(response.tables) } void main() ``` -------------------------------- ### Start Conversation Source: https://github.com/botpress/docs/blob/master/snippets/integrations/cards/botpress/whatsapp.mdx Proactively starts a conversation with a WhatsApp user by sending them a message using a WhatsApp Message Template. ```APIDOC ## Start Conversation ### Description Proactively starts a conversation with a WhatsApp user by sending them a message using a WhatsApp Message Template. ### Method POST ### Endpoint /api/v1/whatsapp/conversations/start ### Parameters #### Request Body - **conversation** (object) - Required - Details of the conversation - **userPhone** (string) - Required - Phone number of the WhatsApp user to start a conversation with. Add the country code (e.g. +81 for japan) - **templateName** (string) - Required - Name of the WhatsApp Message Template to start the conversation with - **templateLanguage** (string) - Optional - Language of the WhatsApp Message Template to start the conversation with. Defaults to "en" (English) - **templateVariablesJson** (string) - Deprecated: use templateBodyParams instead. JSON array of body variable values: ["val1", "val2"]. - **templateHeaderParams** (object | object | object | object) - Optional - Header parameter. For text headers: type="text", value is the replacement text, parameterName is optional (for named params). For media headers: type="image"|"video"|"document", url is the media URL. Documents may include a filename. - **templateBodyParams** (object | object) - Optional - Body parameters. For positional params ({{1}}, {{2}}, ...): type="positional", values is an ordered array of strings. For named params ({{buyer_name}}): type="named", values is a record mapping param names to values. - **templateButtonParams** (array) - Optional - Button parameters as an ordered array. url: value is the URL suffix. quick_reply: payload is the callback data. copy_code: code is the coupon code. skip: no parameter needed (for phone number buttons, etc.). - **type** (string) - Required - **value** (string) - Required (for url type) - **payload** (string) - Required (for quick_reply type) - **code** (string) - Required (for copy_code type) - **botPhoneNumberId** (string) - Optional - Phone number ID to use as sender (uses the default phone number ID if not provided) ### Response #### Success Response (200) - **conversationId** (string) - The Botpress ID of the created conversation - **messageId** (string) - ID of the message created ### Response Example ```json { "conversationId": "65a7b1b3e4f5d6a7b8c9d0e1", "messageId": "65a7b1b3e4f5d6a7b8c9d0e2" } ``` ``` -------------------------------- ### Initialize MCP Server Configuration Source: https://github.com/botpress/docs/blob/master/adk/ai-native/skills.mdx Generates MCP (Model Context Protocol) server configuration files for various AI assistants. This allows assistants live access to your running project. ```bash adk mcp:init --all ```