Adk

Overview

The @toolbox-sdk/adk package provides a Javascript interface to the MCP Toolbox service, enabling you to load and invoke tools from your own applications.

Supported Environments

This SDK is a standard Node.js package built with TypeScript, ensuring broad compatibility with the modern JavaScript ecosystem.

• Node.js: Actively supported on Node.js v18.x and higher. The package is compatible with both modern ES Module (import) and legacy CommonJS (require).
• TypeScript: The SDK is written in TypeScript and ships with its own type declarations, providing a first-class development experience with autocompletion and type-checking out of the box.
• JavaScript: Fully supports modern JavaScript in Node.js environments.

Installation

npm install @toolbox-sdk/adk

Quickstart

1. Start the Toolbox Service

   • Make sure the MCP Toolbox service is running. See the Toolbox Getting Started Guide.

2. Minimal Example

Here’s a minimal example to get you started. Ensure your Toolbox service is running and accessible.

import { ToolboxClient } from '@toolbox-sdk/adk';  
const client = new ToolboxClient(URL);  

async function quickstart() {  
  try {  
      const tools = await client.loadToolset();  
      // Use tools  
  } catch (error) {  
      console.error("unable to load toolset:", error.message);  
  }  
}  
quickstart();  

Usage

Import and initialize a Toolbox client, pointing it to the URL of your running Toolbox service.

import { ToolboxClient } from '@toolbox-sdk/adk';

// Replace with the actual URL where your Toolbox service is running
const URL = 'http://127.0.0.1:5000';

let client = new ToolboxClient(URL);
const tools = await client.loadToolset();

// Use the client and tools as per requirement

All interactions for loading and invoking tools happen through this client.

Transport Protocols

The SDK supports multiple transport protocols to communicate with the Toolbox server. You can specify the protocol version during client initialization.

Available Protocols

• Protocol.MCP: The default protocol version (currently aliases to MCP_v20250618).
• Protocol.MCP_v20241105: Use this for compatibility with older MCP servers (November 2024 version).
• Protocol.MCP_v20250326: March 2025 version.
• Protocol.MCP_v20250618: June 2025 version.
• Protocol.MCP_v20251125: November 2025 version.
• Protocol.TOOLBOX: Legacy Toolbox protocol.

Specifying a Protocol

You can explicitly set the protocol by passing the protocol argument to the ToolboxClient constructor.

import { ToolboxClient, Protocol } from '@toolbox-sdk/adk';

const URL = 'http://127.0.0.1:5000';

// Initialize with a specific protocol version
const client = new ToolboxClient(URL, null, null, Protocol.MCP_v20241105);

const tools = await client.loadToolset();

Loading Tools

You can load tools individually or in groups (toolsets) as defined in your Toolbox service configuration. Loading a toolset is convenient when working with multiple related functions, while loading a single tool offers more granular control.

Load a toolset

A toolset is a collection of related tools. You can load all tools in a toolset or a specific one:

// Load all tools
const tools = await toolbox.loadToolset()

// Load a specific toolset
const tools = await toolbox.loadToolset("my-toolset")

Load a single tool

Loads a specific tool by its unique name. This provides fine-grained control.

const tool = await toolbox.loadTool("my-tool")

Invoking Tools

Once loaded, tools behave like awaitable JS functions. You invoke them using await and pass arguments corresponding to the parameters defined in the tool’s configuration within the Toolbox service.

const tool = await toolbox.loadTool("my-tool")
const result = await tool.runAsync(args: {a: 5, b: 2})

Client to Server Authentication

This section describes how to authenticate the ToolboxClient itself when connecting to a Toolbox server instance that requires authentication. This is crucial for securing your Toolbox server endpoint, especially when deployed on platforms like Cloud Run, GKE, or any environment where unauthenticated access is restricted.

This client-to-server authentication ensures that the Toolbox server can verify the identity of the client making the request before any tool is loaded or called. It is different from Authenticating Tools, which deals with providing credentials for specific tools within an already connected Toolbox session.

When is Client-to-Server Authentication Needed?

You’ll need this type of authentication if your Toolbox server is configured to deny unauthenticated requests. For example:

• Your Toolbox server is deployed on Cloud Run and configured to “Require authentication.”
• Your server is behind an Identity-Aware Proxy (IAP) or a similar authentication layer.
• You have custom authentication middleware on your self-hosted Toolbox server.

Without proper client authentication in these scenarios, attempts to connect or make calls (like load_tool) will likely fail with Unauthorized errors.

How it works

The ToolboxClient allows you to specify functions that dynamically generate HTTP headers for every request sent to the Toolbox server. The most common use case is to add an Authorization header with a bearer token (e.g., a Google ID token).

These header-generating functions are called just before each request, ensuring that fresh credentials or header values can be used.

Configuration

You can configure these dynamic headers as seen below:

import { ToolboxClient } from '@toolbox-sdk/adk';
import {getGoogleIdToken} from '@toolbox-sdk/core/auth'

const URL = 'http://127.0.0.1:5000';
const getGoogleIdTokenGetter = () => getGoogleIdToken(URL);
const client = new ToolboxClient(URL, null, {"Authorization": getGoogleIdTokenGetter});

// Use the client as usual

Authenticating with Google Cloud Servers

For Toolbox servers hosted on Google Cloud (e.g., Cloud Run) and requiring Google ID token authentication, the helper module auth_methods provides utility functions.

Step by Step Guide for Cloud Run

1. Configure Permissions: Grant the roles/run.invoker IAM role on the Cloud Run service to the principal. This could be your user account email or a service account.

2. Configure Credentials

   • Local Development: Set up ADC.
   • Google Cloud Environments: When running within Google Cloud (e.g., Compute Engine, GKE, another Cloud Run service, Cloud Functions), ADC is typically configured automatically, using the environment’s default service account.

3. Connect to the Toolbox Server

   import { ToolboxClient } from '@toolbox-sdk/adk';
   import {getGoogleIdToken} from '@toolbox-sdk/core/auth'
   
   const URL = 'http://127.0.0.1:5000';
   const getGoogleIdTokenGetter = () => getGoogleIdToken(URL);
   const client = new ToolboxClient(URL, null, {"Authorization": getGoogleIdTokenGetter});
   
   // Use the client as usual
   

Authenticating Tools

Tools can be configured within the Toolbox service to require authentication, ensuring only authorized users or applications can invoke them, especially when accessing sensitive data.

When is Authentication Needed?

Authentication is configured per-tool within the Toolbox service itself. If a tool you intend to use is marked as requiring authentication in the service, you must configure the SDK client to provide the necessary credentials (currently Oauth2 tokens) when invoking that specific tool.

Supported Authentication Mechanisms

The Toolbox service enables secure tool usage through Authenticated Parameters. For detailed information on how these mechanisms work within the Toolbox service and how to configure them, please refer to Toolbox Service Documentation - Authenticated Parameters

Step 1: Configure Tools in Toolbox Service

First, ensure the target tool(s) are configured correctly in the Toolbox service to require authentication. Refer to the Toolbox Service Documentation - Authenticated Parameters for instructions.

Step 2: Configure SDK Client

Your application needs a way to obtain the required Oauth2 token for the authenticated user. The SDK requires you to provide a function capable of retrieving this token when the tool is invoked.

Provide an ID Token Retriever Function

You must provide the SDK with a function (sync or async) that returns the necessary token when called. The implementation depends on your application’s authentication flow (e.g., retrieving a stored token, initiating an OAuth flow).

async function getAuthToken() {
    // ... Logic to retrieve ID token (e.g., from local storage, OAuth flow)
    // This example just returns a placeholder. Replace with your actual token retrieval.
    return "YOUR_ID_TOKEN" // Placeholder
}    

Option A: Add Authentication to a Loaded Tool

You can add the token retriever function to a tool object after it has been loaded. This modifies the specific tool instance.

const URL = 'http://127.0.0.1:5000';
let client = new ToolboxClient(URL);
let tool = await client.loadTool("my-tool")

const authTool = tool.addAuthTokenGetter("my_auth", get_auth_token)  // Single token

// OR

const multiAuthTool = tool.addAuthTokenGetters({
    "my_auth_1": getAuthToken1,
    "my_auth_2": getAuthToken2,
})  // Multiple tokens

Option B: Add Authentication While Loading Tools

You can provide the token retriever(s) directly during the loadTool or loadToolset calls. This applies the authentication configuration only to the tools loaded in that specific call, without modifying the original tool objects if they were loaded previously.

const authTool = await toolbox.loadTool("toolName", {"myAuth": getAuthToken})

// OR

const authTools = await toolbox.loadToolset({"myAuth": getAuthToken})

Complete Authentication Example

import { ToolboxClient } from '@toolbox-sdk/adk';

async function getAuthToken() {
    // ... Logic to retrieve ID token (e.g., from local storage, OAuth flow)
    // This example just returns a placeholder. Replace with your actual token retrieval.
    return "YOUR_ID_TOKEN" // Placeholder
}

const URL = 'http://127.0.0.1:5000';
let client = new ToolboxClient(URL);
const tool = await client.loadTool("my-tool");
const authTool = tool.addAuthTokenGetters({"my_auth": getAuthToken});
const result = await authTool.runAsync(args: {input:"some input"});
console.log(result);

Binding Parameter Values

The SDK allows you to pre-set, or “bind”, values for specific tool parameters before the tool is invoked or even passed to an LLM. These bound values are fixed and will not be requested or modified by the LLM during tool use.

Why Bind Parameters?

• Protecting sensitive information: API keys, secrets, etc.
• Enforcing consistency: Ensuring specific values for certain parameters.
• Pre-filling known data: Providing defaults or context.

Option A: Binding Parameters to a Loaded Tool

Bind values to a tool object after it has been loaded. This modifies the specific tool instance.

import { ToolboxClient } from '@toolbox-sdk/adk';

const URL = 'http://127.0.0.1:5000';
let client = new ToolboxClient(URL);
const tool = await client.loadTool("my-tool");

const boundTool = tool.bindParam("param", "value");

// OR

const boundTool = tool.bindParams({"param": "value"});

Option B: Binding Parameters While Loading Tools

Specify bound parameters directly when loading tools. This applies the binding only to the tools loaded in that specific call.

const boundTool = await client.loadTool("my-tool", null, {"param": "value"})

// OR

const boundTools = await client.loadToolset(null, {"param": "value"})

Binding Dynamic Values

Instead of a static value, you can bind a parameter to a synchronous or asynchronous function. This function will be called each time the tool is invoked to dynamically determine the parameter’s value at runtime.

async function getDynamicValue() {
    // Logic to determine the value
    return "dynamicValue";
}

const dynamicBoundTool = tool.bindParam("param", getDynamicValue)

Using with ADK

ADK JS:

import {FunctionTool, InMemoryRunner, LlmAgent} from '@google/adk';
import {Content} from '@google/genai';
import {ToolboxClient} from '@toolbox-sdk/core'

const toolboxClient = new ToolboxClient("http://127.0.0.1:5000");
const loadedTools = await toolboxClient.loadToolset();

export const rootAgent = new LlmAgent({
  name: 'weather_time_agent',
  model: 'gemini-2.5-flash',
  description:
    'Agent to answer questions about the time and weather in a city.',
  instruction:
    'You are a helpful agent who can answer user questions about the time and weather in a city.',
  tools: loadedTools,
});

async function main() {
  const userId = 'test_user';
  const appName = rootAgent.name;
  const runner = new InMemoryRunner({agent: rootAgent, appName});
  const session = await runner.sessionService.createSession({
    appName,
    userId,
  });

  const prompt = 'What is the weather in New York? And the time?';
  const content: Content = {
    role: 'user',
    parts: [{text: prompt}],
  };
  console.log(content);
  for await (const e of runner.runAsync({
    userId,
    sessionId: session.id,
    newMessage: content,
  })) {
    if (e.content?.parts?.[0]?.text) {
      console.log(`${e.author}: ${JSON.stringify(e.content, null, 2)}`);
    }
  }
}

main().catch(console.error);