MCP Toolbox for Databases Server

Untuk menginstal Toolbox sebagai binari:

Linux (AMD64)

Untuk menginstal Toolbox sebagai binari di Linux (AMD64):

# lihat halaman rilis untuk versi lain
export VERSION=1.4.0
curl -L -o toolbox https://storage.googleapis.com/mcp-toolbox-for-databases/v$VERSION/linux/amd64/toolbox
chmod +x toolbox

macOS (Apple Silicon)

Untuk menginstal Toolbox sebagai binari di macOS (Apple Silicon):

# lihat halaman rilis untuk versi lain
export VERSION=1.4.0
curl -L -o toolbox https://storage.googleapis.com/mcp-toolbox-for-databases/v$VERSION/darwin/arm64/toolbox
chmod +x toolbox

macOS (Intel)

Untuk menginstal Toolbox sebagai binari di macOS (Intel):

# lihat halaman rilis untuk versi lain
export VERSION=1.4.0
curl -L -o toolbox https://storage.googleapis.com/mcp-toolbox-for-databases/v$VERSION/darwin/amd64/toolbox
chmod +x toolbox

Windows (Command Prompt)

Untuk menginstal Toolbox sebagai binari di Windows (Command Prompt):

:: lihat halaman rilis untuk versi lain
set VERSION=1.4.0
curl -o toolbox.exe "https://storage.googleapis.com/mcp-toolbox-for-databases/v%VERSION%/windows/amd64/toolbox.exe"

Windows (PowerShell)

Untuk menginstal Toolbox sebagai binari di Windows (PowerShell):

# lihat halaman rilis untuk versi lain
$VERSION = "1.4.0"
curl.exe -o toolbox.exe "https://storage.googleapis.com/mcp-toolbox-for-databases/v$VERSION/windows/amd64/toolbox.exe"

Windows ARM64 (Command Prompt)

Untuk menginstal Toolbox sebagai binari di Windows ARM64 (Command Prompt):

:: lihat halaman rilis untuk versi lain
set VERSION=1.4.0
curl -o toolbox.exe "https://storage.googleapis.com/mcp-toolbox-for-databases/v%VERSION%/windows/arm64/toolbox.exe"

Windows ARM64 (PowerShell)

Untuk menginstal Toolbox sebagai binari di Windows ARM64 (PowerShell):

# lihat halaman rilis untuk versi lain
$VERSION = "1.4.0"
curl.exe -o toolbox.exe "https://storage.googleapis.com/mcp-toolbox-for-databases/v$VERSION/windows/arm64/toolbox.exe"

# see releases page for other versions
export VERSION=1.4.0
docker pull us-central1-docker.pkg.dev/database-toolbox/toolbox/toolbox:$VERSION

Untuk menginstal Toolbox menggunakan Homebrew di macOS atau Linux:

brew install mcp-toolbox

Untuk menginstal dari sumber, pastikan Anda memiliki versi terbaru dari Go terinstal, lalu jalankan perintah berikut:

go install github.com/googleapis/[email protected]

# Install Gemini CLI
npm install -g @google/gemini-cli
# Install the extension
gemini extensions install https://github.com/gemini-cli-extensions/cloud-sql-postgres
# Run Gemini CLI
gemini

Berinteraksi dengan alat kustom Anda menggunakan bahasa alami melalui Gemini CLI.

# Install the extension
gemini extensions install https://github.com/gemini-cli-extensions/mcp-toolbox

Untuk menjalankan Toolbox dari binari:

./toolbox --config "tools.yaml"

ⓘ Catatan Toolbox mengaktifkan pemuatan ulang dinamis secara default. Untuk menonaktifkannya, gunakan flag --disable-reload.

Untuk menjalankan server setelah menarik image kontainer:

export VERSION=0.24.0 # Use the version you pulled
docker run -p 5000:5000 \
-v $(pwd)/tools.yaml:/app/tools.yaml \
us-central1-docker.pkg.dev/database-toolbox/toolbox/toolbox:$VERSION \
--config "/app/tools.yaml"

ⓘ Catatan Flag -v memasang tools.yaml lokal Anda ke dalam kontainer, dan -p memetakan port kontainer 5000 ke port host Anda 5000.

Untuk menjalankan server langsung dari sumber, arahkan ke direktori root proyek dan jalankan:

go run .

ⓘ Catatan Perintah ini menjalankan proyek dari sumber, dan lebih cocok untuk pengembangan dan pengujian. Ini tidak mengkompilasi binari ke dalam $GOPATH Anda. Jika Anda ingin mengkompilasi binari sebagai gantinya, lihat Dokumentasi Pengembang.

Jika Anda menginstal Toolbox menggunakan Homebrew, binari toolbox tersedia di jalur sistem Anda. Anda dapat memulai server dengan perintah yang sama:

toolbox --config "tools.yaml"

# Run Gemini CLI
gemini

# List extensions
/extensions list
# List MCP servers
/mcp list

Core

1. Pasang Toolbox Core SDK:

   pip install toolbox-core
   

2. Muat alat:

   from toolbox_core import ToolboxClient
   
   # update the url to point to your server
   async with ToolboxClient("http://127.0.0.1:5000") as client:
   
       # these tools can be passed to your application!
       tools = await client.load_toolset("toolset_name")
   

Untuk petunjuk lebih rinci tentang penggunaan Toolbox Core SDK, lihat README proyek.

LangChain / LangGraph

1. Pasang Toolbox LangChain SDK:

   pip install toolbox-langchain
   

2. Muat alat:

   from toolbox_langchain import ToolboxClient
   
   # update the url to point to your server
   async with ToolboxClient("http://127.0.0.1:5000") as client:
   
       # these tools can be passed to your application!
       tools = client.load_toolset()
   

   Untuk petunjuk lebih rinci tentang penggunaan Toolbox LangChain SDK, lihat README proyek.

LlamaIndex

1. Pasang Toolbox Llamaindex SDK:

   pip install toolbox-llamaindex
   

2. Muat alat:

   from toolbox_llamaindex import ToolboxClient
   
   # update the url to point to your server
   async with ToolboxClient("http://127.0.0.1:5000") as client:
   
       # these tools can be passed to your application!
       tools = client.load_toolset()
   

   Untuk petunjuk lebih rinci tentang penggunaan Toolbox Llamaindex SDK, lihat README proyek.

Core

1. Pasang Toolbox Core SDK:

   npm install @toolbox-sdk/core
   

2. Muat alat:

   import { ToolboxClient } from '@toolbox-sdk/core';
   
   // update the url to point to your server
   const URL = 'http://127.0.0.1:5000';
   let client = new ToolboxClient(URL);
   
   // these tools can be passed to your application!
   const tools = await client.loadToolset('toolsetName');
   

   Untuk petunjuk lebih rinci tentang penggunaan Toolbox Core SDK, lihat README proyek.

LangChain / LangGraph

1. Pasang Toolbox Core SDK:

   npm install @toolbox-sdk/core
   

2. Muat alat:

   import { ToolboxClient } from '@toolbox-sdk/core';
   
   // update the url to point to your server
   const URL = 'http://127.0.0.1:5000';
   let client = new ToolboxClient(URL);
   
   // these tools can be passed to your application!
   const toolboxTools = await client.loadToolset('toolsetName');
   
   // Define the basics of the tool: name, description, schema and core logic
   const getTool = (toolboxTool) => tool(currTool, {
       name: toolboxTool.getName(),
       description: toolboxTool.getDescription(),
       schema: toolboxTool.getParamSchema()
   });
   
   // Use these tools in your Langchain/Langraph applications
   const tools = toolboxTools.map(getTool);
   

Genkit

1. Pasang Toolbox Core SDK:

   npm install @toolbox-sdk/core
   

2. Muat alat:

   import { ToolboxClient } from '@toolbox-sdk/core';
   import { genkit } from 'genkit';
   
   // Initialise genkit
   const ai = genkit({
       plugins: [
           googleAI({
               apiKey: process.env.GEMINI_API_KEY || process.env.GOOGLE_API_KEY
           })
       ],
       model: googleAI.model('gemini-2.0-flash'),
   });
   
   // update the url to point to your server
   const URL = 'http://127.0.0.1:5000';
   let client = new ToolboxClient(URL);
   
   // these tools can be passed to your application!
   const toolboxTools = await client.loadToolset('toolsetName');
   
   // Define the basics of the tool: name, description, schema and core logic
   const getTool = (toolboxTool) => ai.defineTool({
       name: toolboxTool.getName(),
       description: toolboxTool.getDescription(),
       schema: toolboxTool.getParamSchema()
   }, toolboxTool)
   
   // Use these tools in your Genkit applications
   const tools = toolboxTools.map(getTool);
   

ADK

1. Pasang Toolbox ADK SDK:

   npm install @toolbox-sdk/adk
   

2. Muat alat:

   import { ToolboxClient } from '@toolbox-sdk/adk';
   
   // update the url to point to your server
   const URL = 'http://127.0.0.1:5000';
   let client = new ToolboxClient(URL);
   
   // these tools can be passed to your application!
   const tools = await client.loadToolset('toolsetName');
   

   Untuk petunjuk lebih rinci tentang penggunaan Toolbox ADK SDK, lihat README proyek.

Core

1. Pasang Toolbox Go SDK:

   go get github.com/googleapis/mcp-toolbox-sdk-go
   

2. Muat alat:

   package main
   
   import (
     "github.com/googleapis/mcp-toolbox-sdk-go/core"
     "context"
   )
   
   func main() {
     // Make sure to add the error checks
     // update the url to point to your server
     URL := "http://127.0.0.1:5000";
     ctx := context.Background()
   
     client, err := core.NewToolboxClient(URL)
   
     // Framework agnostic tools
     tools, err := client.LoadToolset("toolsetName", ctx)
   }
   

   Untuk petunjuk lebih rinci tentang penggunaan Toolbox Go SDK, lihat README proyek.

LangChain Go

1. Pasang Toolbox Go SDK:

   go get github.com/googleapis/mcp-toolbox-sdk-go
   

2. Muat alat:

   package main
   
   import (
     "context"
     "encoding/json"
   
     "github.com/googleapis/mcp-toolbox-sdk-go/core"
     "github.com/tmc/langchaingo/llms"
   )
   
   func main() {
     // Make sure to add the error checks
     // update the url to point to your server
     URL := "http://127.0.0.1:5000"
     ctx := context.Background()
   
     client, err := core.NewToolboxClient(URL)
   
     // Framework agnostic tool
     tool, err := client.LoadTool("toolName", ctx)
   
     // Fetch the tool's input schema
     inputschema, err := tool.InputSchema()
   
     var paramsSchema map[string]any
     _ = json.Unmarshal(inputschema, &paramsSchema)
   
     // Use this tool with LangChainGo
     langChainTool := llms.Tool{
       Type: "function",
       Function: &llms.FunctionDefinition{
         Name:        tool.Name(),
         Description: tool.Description(),
         Parameters:  paramsSchema,
       },
     }
   }
   
   

Genkit

1. Pasang Toolbox Go SDK:

   go get github.com/googleapis/mcp-toolbox-sdk-go
   

2. Muat alat:

   package main
   import (
     "context"
     "log"
   
     "github.com/firebase/genkit/go/genkit"
     "github.com/googleapis/mcp-toolbox-sdk-go/core"
     "github.com/googleapis/mcp-toolbox-sdk-go/tbgenkit"
   )
   
   func main() {
     // Make sure to add the error checks
     // Update the url to point to your server
     URL := "http://127.0.0.1:5000"
     ctx := context.Background()
     g := genkit.Init(ctx)
   
     client, err := core.NewToolboxClient(URL)
   
     // Framework agnostic tool
     tool, err := client.LoadTool("toolName", ctx)
   
     // Convert the tool using the tbgenkit package
     // Use this tool with Genkit Go
     genkitTool, err := tbgenkit.ToGenkitTool(tool, g)
     if err != nil {
       log.Fatalf("Failed to convert tool: %v\n", err)
     }
     log.Printf("Successfully converted tool: %s", genkitTool.Name())
   }
   

Go GenAI

1. Pasang Toolbox Go SDK:

   go get github.com/googleapis/mcp-toolbox-sdk-go
   

2. Muat alat:

   package main
   
   import (
     "context"
     "encoding/json"
   
     "github.com/googleapis/mcp-toolbox-sdk-go/core"
     "google.golang.org/genai"
   )
   
   func main() {
     // Make sure to add the error checks
     // Update the url to point to your server
     URL := "http://127.0.0.1:5000"
     ctx := context.Background()
   
     client, err := core.NewToolboxClient(URL)
   
     // Framework agnostic tool
     tool, err := client.LoadTool("toolName", ctx)
   
     // Fetch the tool's input schema
     inputschema, err := tool.InputSchema()
   
     var schema *genai.Schema
     _ = json.Unmarshal(inputschema, &schema)
   
     funcDeclaration := &genai.FunctionDeclaration{
       Name:        tool.Name(),
       Description: tool.Description(),
       Parameters:  schema,
     }
   
     // Use this tool with Go GenAI
     genAITool := &genai.Tool{
       FunctionDeclarations: []*genai.FunctionDeclaration{funcDeclaration},
     }
   }
   

OpenAI Go

1. Pasang Toolbox Go SDK:

   go get github.com/googleapis/mcp-toolbox-sdk-go
   

2. Muat alat:

   package main
   
   import (
     "context"
     "encoding/json"
   
     "github.com/googleapis/mcp-toolbox-sdk-go/core"
     openai "github.com/openai/openai-go"
   )
   
   func main() {
     // Make sure to add the error checks
     // Update the url to point to your server
     URL := "http://127.0.0.1:5000"
     ctx := context.Background()
   
     client, err := core.NewToolboxClient(URL)
   
     // Framework agnostic tool
     tool, err := client.LoadTool("toolName", ctx)
   
     // Fetch the tool's input schema
     inputschema, err := tool.InputSchema()
   
     var paramsSchema openai.FunctionParameters
     _ = json.Unmarshal(inputschema, &paramsSchema)
   
     // Use this tool with OpenAI Go
     openAITool := openai.ChatCompletionToolParam{
       Function: openai.FunctionDefinitionParam{
         Name:        tool.Name(),
         Description: openai.String(tool.Description()),
         Parameters:  paramsSchema,
       },
     }
   
   }
   

ADK Go

1. Pasang Toolbox Go SDK:

   go get github.com/googleapis/mcp-toolbox-sdk-go
   

2. Muat alat:

   package main
   
   import (
     "github.com/googleapis/mcp-toolbox-sdk-go/tbadk"
     "context"
   )
   
   func main() {
     // Make sure to add the error checks
     // Update the url to point to your server
     URL := "http://127.0.0.1:5000"
     ctx := context.Background()
     client, err := tbadk.NewToolboxClient(URL)
     if err != nil {
       return fmt.Sprintln("Could not start Toolbox Client", err)
     }
   
     // Use this tool with ADK Go
     tool, err := client.LoadTool("toolName", ctx)
     if err != nil {
       return fmt.Sprintln("Could not load Toolbox Tool", err)
     }
   }
   

   Untuk petunjuk lebih rinci tentang penggunaan Toolbox Go SDK, lihat README proyek.