### Start Frontend Source: https://auth0.com/ai/docs/get-started/call-your-apis-on-users-behalf Starts the frontend development server. This involves copying the environment file, installing dependencies, and running the development script. ```bash cd frontend cp .env.example .env # Copy the `.env.example` file to `.env`. npm install npm run dev ``` -------------------------------- ### Frontend Environment File Setup Source: https://auth0.com/ai/docs/get-started/call-others-apis-on-users-behalf Copy the example environment file to .env in the frontend directory. No further customization is typically required for the frontend environment. ```bash # In the frontend directory of your project, copy the .env.example file to .env. # No further customization required. ``` -------------------------------- ### Database and Application Setup (Bash) Source: https://auth0.com/ai/docs/get-started/authorization-for-rag Commands to start the PostgreSQL database and create the necessary database schema for the application. ```bash # start the postgres database docker compose up -d # create the database schema npm run db:migrate ``` -------------------------------- ### Start FastAPI Backend Source: https://auth0.com/ai/docs/get-started/call-others-apis-on-users-behalf Run the FastAPI backend server. Ensure you are in the backend directory, activate your virtual environment, install dependencies, and then start the development server. ```bash cd backend source .venv/bin/activate uv pip install auth0_fastapi fastapi dev app/main.py ``` -------------------------------- ### Start LangGraph Server Source: https://auth0.com/ai/docs/get-started/call-others-apis-on-users-behalf Start the local LangGraph server. This command installs the necessary packages and runs the LangGraph development server on a specified port. ```bash cd backend source .venv/bin/activate uv pip install -U langgraph-api langgraph dev --port 54367 --allow-blocking ``` -------------------------------- ### Install Backend Packages with uv Source: https://auth0.com/ai/docs/get-started/user-authentication Navigate to the backend directory and install required packages using uv. ```bash cd backend uv sync ``` -------------------------------- ### Start LangGraph Server Source: https://auth0.com/ai/docs/get-started/call-your-apis-on-users-behalf Starts the LangGraph server. This command also installs the necessary `langgraph-api` package. The `--allow-blocking` flag is used for development. ```bash cd backend source .venv/bin/activate uv pip install -U langgraph-api langgraph dev --port 54367 --allow-blocking ``` -------------------------------- ### Install Frontend Packages Source: https://auth0.com/ai/docs/get-started/call-others-apis-on-users-behalf Navigate to the frontend directory and install the necessary npm packages to run the frontend application. ```bash cd frontend npm install ``` -------------------------------- ### Install Frontend Packages with npm Source: https://auth0.com/ai/docs/get-started/user-authentication Navigate to the frontend directory and install required packages using npm. ```bash cd frontend npm install ``` -------------------------------- ### Install Project Dependencies Source: https://auth0.com/ai/docs/get-started/user-authentication Install all necessary packages for the project. Ensure npm is installed. ```bash npm install ``` -------------------------------- ### Install Project Dependencies Source: https://auth0.com/ai/docs/get-started/call-others-apis-on-users-behalf Install all required client and server dependencies from the root directory of your project using npm. ```bash # Install all client & server dependencies from the root directory of the project. npm install ``` -------------------------------- ### Install Dependencies with uv Source: https://auth0.com/ai/docs/get-started/asynchronous-authorization Install necessary Python packages for the backend, including the Auth0 AI SDK for LangChain and LangGraph. Ensure uv is installed and use the provided command to add the packages. ```bash cd backend uv sync uv add "auth0-ai-langchain>=1.0.1" "langgraph>=0.5.4" langchain-openai "langgraph-cli[inmem]>=0.3.6" --prerelease=allow ``` -------------------------------- ### Run OpenFGA Server using Homebrew Source: https://auth0.com/ai/docs/mcp/get-started/secure-mcp-server-with-auth0-fga Start the OpenFGA server locally using the Homebrew installation. Ensure this runs in a separate terminal. ```shell openfga run ``` -------------------------------- ### Start FastAPI Backend Source: https://auth0.com/ai/docs/get-started/authorization-for-rag Commands to start the FastAPI backend, including setting up the Docker Compose environment for the database. ```bash cd backend # start the postgres database docker compose up -d # start the FastAPI backend source .venv/bin/activate fastapi dev app/main.py ``` -------------------------------- ### Install OpenFGA using Homebrew Source: https://auth0.com/ai/docs/mcp/get-started/secure-mcp-server-with-auth0-fga Use Homebrew to install the OpenFGA CLI. This is one of the methods for setting up OpenFGA locally. ```shell brew install openfga ``` -------------------------------- ### Install Node.js Auth0 SDK Source: https://auth0.com/ai/docs/sdks/javascript-sdk Install the Auth0 Node.js SDK to streamline authentication and authorization in Node.js applications. ```bash npm install auth0 ``` -------------------------------- ### Install Auth0 AI SDK Source: https://auth0.com/ai/docs/sdks/javascript-sdk Install the Auth0 AI SDK for base abstractions for authentication and authorization in AI applications. ```bash npm install @auth0/ai ``` -------------------------------- ### Install Auth0 AI Components and Add TokenVault Source: https://auth0.com/ai/docs/get-started/call-others-apis-on-users-behalf Install the necessary Auth0 AI packages and add the TokenVault component to your project. Run these commands in your frontend directory. ```bash cd frontend npm install @auth0/ai @langchain/langgraph-sdk npx @auth0/ai-components add TokenVault ``` -------------------------------- ### Install Auth0 Next.js SDK Source: https://auth0.com/ai/docs/get-started/user-authentication Install version 4 of the Auth0 Next.js SDK to integrate authentication features into your project. ```bash npm i @auth0/nextjs-auth0@4 ``` -------------------------------- ### Install Required Packages Source: https://auth0.com/ai/docs/get-started/call-others-apis-on-users-behalf Install the Auth0 AI SDK for Vercel AI and other necessary dependencies using npm. ```bash npm install @auth0/ai-vercel@5 ai@6 @ai-sdk/openai@3 @ai-sdk/react@3 zod@3.25.76 googleapis@161 ``` -------------------------------- ### Install Specific Auth0 and LangChain Packages Source: https://auth0.com/ai/docs/get-started/call-others-apis-on-users-behalf Install the Auth0 AI SDK for LangChain and other required LangChain libraries with specific versions. ```bash npm install @auth0/ai-langchain@4 @langchain/community@0.3.53 @langchain/core@0.3.77 @langchain/langgraph@0.4.4 @langchain/openai@0.6.13 langchain@0.3.12 langgraph-nextjs-api-passthrough@0.1.4 ``` -------------------------------- ### Install Auth0 Fastify SDK Source: https://auth0.com/ai/docs/sdks/javascript-sdk Install the Auth0 Fastify SDK to streamline authentication and authorization in Fastify applications. ```bash npm i @auth0/auth0-fastify ``` -------------------------------- ### Install Backend Dependencies (Bash) Source: https://auth0.com/ai/docs/get-started/authorization-for-rag Installs required Python dependencies for the backend, including Auth0 AI SDK, LangGraph, and OpenAI provider, using uv. ```bash cd backend uv sync uv add "auth0-ai-langchain>=1.0.1" openfga-sdk langgraph langchain-openai "langgraph-cli[inmem]" --prerelease=allow ``` -------------------------------- ### Install Auth0 Server Python SDK Source: https://auth0.com/ai/docs/sdks/python-sdk Use this command to install the Auth0 Server Python SDK for user authentication in Python applications. ```bash pip install auth0-server-python ``` -------------------------------- ### Install Auth0 FastAPI SDK Source: https://auth0.com/ai/docs/sdks/python-sdk Install the Auth0 FastAPI SDK to implement user authentication in FastAPI web applications using Auth0. ```bash pip install auth0-fastapi ``` -------------------------------- ### Install Auth0 API Python SDK Source: https://auth0.com/ai/docs/sdks/python-sdk Install the auth0-api-python library to secure APIs running on Python and verify Auth0-issued access tokens. ```bash pip install auth0-api-python ``` -------------------------------- ### Install Auth0 AI SDK Source: https://auth0.com/ai/docs/sdks/python-sdk Install the Auth0 AI SDK for base abstractions in authentication and authorization for AI applications, including CIBA protocol support and OpenFGA integration. ```bash pip install auth0-ai ``` -------------------------------- ### Install FGA CLI on Linux Source: https://auth0.com/ai/docs/mcp/get-started/secure-mcp-server-with-auth0-fga Install the OpenFGA CLI on Linux by downloading the release and adding it to your PATH. This tool is used for managing authorization models and permissions. ```shell # Example for Linux (replace version with latest) wget https://github.com/openfga/cli/releases/download/v0.6.3/fga_0.6.3_linux_amd64.tar.gz tar -xzf fga_0.6.3_linux_amd64.tar.gz sudo mv fga /usr/local/bin/ ``` -------------------------------- ### Install Dependencies for Vercel AI + Next.js Source: https://auth0.com/ai/docs/get-started/asynchronous-authorization Installs the necessary Auth0 AI SDK and Vercel AI SDK packages. Ensure you have the correct versions as specified. ```bash npm install @auth0/ai-vercel@5 ai@6 @ai-sdk/openai@3 @ai-sdk/react@3 zod@3.25.76 ``` -------------------------------- ### Install jq on Linux Source: https://auth0.com/ai/docs/mcp/get-started/authorization-for-your-mcp-server Install the jq command-line JSON processor on Linux using apt-get. This tool helps parse JSON responses from the Auth0 CLI. ```shell sudo apt-get install jq ``` -------------------------------- ### Start Development Server Source: https://auth0.com/ai/docs/get-started/call-others-apis-on-users-behalf Run the client and server simultaneously for development. Navigate to the specified local URL to test the application. ```bash npm run dev ``` -------------------------------- ### Account and Application Setup Steps Source: https://auth0.com/ai/docs/get-started/asynchronous-authorization This component outlines the steps required to create an Auth0 account and configure a new Auth0 application, including setting callback and logout URLs, and managing grant types. ```javascript export const AccountAndAppSteps = ({applicationType = "Regular Web Applications", callbackUrl = "http://localhost:3000/auth/callback", logoutUrl = "http://localhost:3000", appCreation = true, allowedWebOrigins, copyDomain, enableTokenVaultGrant = false, enableRefreshTokenGrant = false, enableAllowRefreshTokenRotation = undefined}) => { const steps = [ To continue with this quickstart, you need to have an{" "} Auth0 account. ]; if (appCreation) { steps.push( Go to your{" "} Auth0 Dashboard {" "} to create a new Auth0 Application. To learn more about Auth0 applications, read{" "} Applications . ); } return steps; }; ``` -------------------------------- ### Auth0 Authentication Setup Source: https://auth0.com/ai/docs/how-tos/list-slack-channels This snippet shows how to set up Auth0 authentication using `@auth0/nextjs-auth0` to get an access token for API calls. Ensure you have the necessary environment variables configured. ```typescript import { auth0 } from "@/lib/auth0"; async function getAccessToken() { const tokenResult = await auth0.getAccessToken(); if (!tokenResult?.token) { throw new Error("Error retrieving access token for langgraph api."); } return tokenResult.token; } export const { GET, POST, PUT, PATCH, DELETE, OPTIONS, runtime } = initApiPassthrough({ apiUrl: process.env.LANGGRAPH_API_URL, apiKey: process.env.LANGSMITH_API_KEY, runtime: "edge", baseRoute: "langgraph/", headers: async (req: NextRequest) => { const headers: Record = {}; req.headers.forEach((value, key) => { headers[key] = value; }); const accessToken = await getAccessToken(); headers["Authorization"] = `Bearer ${accessToken}`; return headers; }, }); ``` -------------------------------- ### Auth0 Setup Block for Social Connections Source: https://auth0.com/ai/docs/integrations/basecamp This React component outlines the steps for setting up a social connection in the Auth0 Dashboard. It guides users through configuring client IDs, secrets, and scopes for various providers. ```javascript export const Auth0SetupBlock = ({providerName, clientIDName = "Client ID", clientSecretName = "Client Secret", scopesName = "Permissions", allowFreeFormScopes = false, allowOfflineAccess = false}) => { return <>
  1. In the Auth0 Dashboard, go to{" "} Authentication > Social.
  2. Select Create Connection, then choose {providerName}.
  3. Click Continue.
  4. In General:
    1. Enter the {clientIDName} and {clientSecretName} from your {providerName} OAuth app.
    2. Under {scopesName}, select the scope(s) required for your application. These determine what permissions your application can request from {providerName}, whether for authentication (such as accessing basic profile details) or for API access (such as connecting to the provider's APIs).

      For a Dropbox and Google social connection, you must select Offline Access in the Auth0 Dashboard, enabling the client application to obtain an Auth0 refresh token.
      3. {allowOfflineAccess &&
    3. Under {scopesName}, enable Offline Access for the connection. This is required by Auth0 to obtain a refresh token from {providerName}.
      4. } {allowFreeFormScopes &&
    4. Add any additional scopes your application requires in the{ ``` ```javascript Additional Scopes field.
      5. }
  5. In Purpose, toggle on Connected Accounts for Token Vault. This lets the connection retrieve and securely store access tokens for external APIs. Learn more in{" "} Connected Accounts for Token Vault .
  6. Click Create.
  7. After creation, you are redirected to the Applications page. Select the application(s) to enable this connection for.
    Note: In a new Auth0 tenant, you can select the Default App.
  8. Once you have created your {providerName} social connection, test your connection to ensure the setup is working correctly before using it in your application.
; }; ``` -------------------------------- ### Run Backend Server Source: https://auth0.com/ai/docs/get-started/user-authentication Start the FastAPI backend server. Ensure you activate the virtual environment first. ```bash cd backend source .venv/bin/activate fastapi dev app/main.py ``` -------------------------------- ### Create New Node.js Project and Install Dependencies Source: https://auth0.com/ai/docs/get-started/asynchronous-authorization Initializes a new Node.js project and installs necessary dependencies including Auth0 SDK, Vercel AI SDK, Zod, and OpenAI provider. ```bash npm init -y npm i auth0@5 @auth0/ai-vercel@5 zod@3.25.76 ai@6 @ai-sdk/openai@3 dotenv@16 ``` -------------------------------- ### Verify FGA CLI Installation Source: https://auth0.com/ai/docs/mcp/get-started/secure-mcp-server-with-auth0-fga Check the installed version of the FGA CLI to confirm the installation was successful. ```shell fga version ``` -------------------------------- ### Install JavaScript Dependencies Source: https://auth0.com/ai/docs/mcp/get-started/authorization-for-your-mcp-server Install the required npm packages for the JavaScript FastMCP MCP server. Ensure you have npm installed before running this command. ```shell npm install ``` -------------------------------- ### Install Python Dependencies Source: https://auth0.com/ai/docs/mcp/get-started/authorization-for-your-mcp-server Install the required packages for the Python FastMCP MCP server using poetry. Ensure you have poetry installed before running this command. ```shell poetry install ``` -------------------------------- ### Clone GitHub Repository for Sample App Source: https://auth0.com/ai/docs/mcp/get-started/secure-mcp-server-with-auth0-fga Clone the repository and navigate to the sample app folder. This sets up the project locally. ```shell git clone https://github.com/auth0-samples/auth0-ai-samples.git cd auth0-ai-samples/auth-for-mcp/fastmcp-mcp-fga-js ``` -------------------------------- ### Run Frontend Development Server Source: https://auth0.com/ai/docs/get-started/user-authentication Start the React frontend development server using npm. ```bash cd frontend npm run dev ``` -------------------------------- ### Run Development Server Source: https://auth0.com/ai/docs/get-started/user-authentication Start the local development server to run your application. Access it via http://localhost:3000. ```bash npm run dev ``` -------------------------------- ### Install Node.js Dependencies Source: https://auth0.com/ai/docs/get-started/authorization-for-rag Install the required npm packages for a Node.js project using LangChain and Auth0 AI. ```bash npm init -y npm install langchain@0.3 @langchain/langgraph@0.2 @auth0/ai-langchain@4 dotenv@16 ``` -------------------------------- ### Install Backend Dependencies Source: https://auth0.com/ai/docs/get-started/call-others-apis-on-users-behalf Install the required Python dependencies in the backend directory using uv. This includes Auth0 AI SDK, LangGraph, OpenAI integration, LangGraph CLI, and Google API client. ```bash cd backend uv sync uv add "auth0-ai-langchain>=1.0.1" "langgraph>=0.5.4" langchain-openai "langgraph-cli[inmem]>=0.3.6" google-api-python-client --prerelease=allow ``` -------------------------------- ### Run JavaScript MCP Server Source: https://auth0.com/ai/docs/mcp/get-started/authorization-for-your-mcp-server Start the JavaScript FastMCP MCP server using the npm start script. ```shell npm run start ``` -------------------------------- ### Complete .env File for OpenFGA (Local) Source: https://auth0.com/ai/docs/mcp/get-started/secure-mcp-server-with-auth0-fga This is an example of a complete .env file when using OpenFGA locally. It includes Auth0 and OpenFGA specific configurations. ```dotenv AUTH0_DOMAIN=YOUR_TENANT.us.auth0.com AUTH0_AUDIENCE=http://localhost:3001/ PORT=3001 MCP_SERVER_URL=http://localhost:3001 # OpenFGA Configuration FGA_API_URL=http://localhost:8080 FGA_STORE_ID=YOUR_STORE_ID ``` -------------------------------- ### Initialize ApiClient with Options Source: https://auth0.com/ai/docs/mcp/get-started/call-your-apis-on-users-behalf Configure the ApiClient with necessary Auth0 credentials including domain, audience, client ID, and client secret. These are typically loaded from environment variables. ```python self.client = ApiClient(ApiClientOptions( domain=domain, # AUTH0_DOMAIN env var audience=audience, # AUTH0_AUDIENCE env var client_id=client_id, # MCP_AUTH0_CLIENT_ID env var client_secret=client_secret # MCP_AUTH0_CLIENT_SECRET env var )) ``` -------------------------------- ### Install Token Vault Component Source: https://auth0.com/ai/docs/how-tos/list-github-repositories This bash command installs the `TokenVault` component from the `@auth0/ai-components` package, which is used for client-side authentication popups. ```bash npx @auth0/ai-components add TokenVault ``` -------------------------------- ### Install Dependencies for LangGraph.js + Next.js Source: https://auth0.com/ai/docs/get-started/authorization-for-rag Install the necessary Auth0 AI SDK, LangChain, and related packages for your LangGraph.js and Next.js project. ```bash npm install @auth0/ai-langchain@4 @langchain/core@0.3.77 @langchain/langgraph@0.4.4 @langchain/openai@0.6.13 langchain@0.3.12 langgraph-nextjs-api-passthrough@0.1.4 ``` -------------------------------- ### LangGraph Workflow Setup Source: https://auth0.com/ai/docs/how-tos/list-github-repositories This snippet shows the setup of a LangGraph workflow, including defining states, nodes for calling LLM and tools, and edges for controlling the flow. It specifically includes the `list_github_repositories_tool`. ```python if isinstance(last_message, AIMessage) and last_message.tool_calls: return "tools" return END workflow = ( StateGraph(State) .add_node("call_llm", call_llm) .add_node( "tools", ToolNode( [ # a tool with Token Vault access list_github_repositories_tool, # ... other tools ], # The error handler should be disabled to # allow interruptions to be triggered from within tools. handle_tool_errors=False ) ) .add_edge(START, "call_llm") .add_edge("tools", "call_llm") .add_conditional_edges("call_llm", route_after_llm, [END, "tools"]) ) graph = workflow.compile(checkpointer=MemorySaver(), store=InMemoryStore()) ```