### Maven: Example output

Source: https://platform.claude.com/docs/pt-BR/get-started

Example output from running the QuickStart program, showing a list of search strategies for renewable energy.

```text
Here are some effective search strategies to find the latest developments in renewable energy:

## General Search Terms
- "Renewable energy news 2025"
- ...
```

--------------------------------

### Bad Example: Assumes Installation

Source: https://platform.claude.com/docs/pt-BR/agents-and-tools/agent-skills/best-practices

Shows an incorrect approach where the skill assumes a package is installed without specifying dependencies.

```markdown
"Use the pdf library to process the file."
```

--------------------------------

### Good Example: Explicit about Dependencies

Source: https://platform.claude.com/docs/pt-BR/agents-and-tools/agent-skills/best-practices

Shows the correct approach: explicitly state the required package installation command and then use it in code. This example uses pypdf to read a PDF file.

```markdown
"Install required package: `pip install pypdf`

Then use it:
```python
from pypdf import PdfReader
reader = PdfReader("file.pdf")
```"
```

--------------------------------

### Run Python ModeAgent example from repository root

Source: https://platform.claude.com/docs/pt-BR/build-with-claude/mid-conversation-effort-example

Starts the Python example from the directory where agents should work, such as the root of a repository to review. With fan-out mode on, the model explores with bash commands, dispatches the Workflow tool unprompted, and synthesizes subagent reports into a final answer.

```bash
python orchestration_mode.py "Review this repository for flaky tests and propose fixes."

```

--------------------------------

### Returns Examples - Response 200

Source: https://platform.claude.com/docs/pt-BR/api/admin/rbac_groups/list

Another example response, identical to the previous one, provided under the Returns Examples section.

```json
{
  "data": [
    {
      "id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF",
      "created_at": "2024-10-30T23:58:27.427722Z",
      "name": "Engineering",
      "roles": [
        "rbac_role_016J8xVtKpDq3Wy9ZmN2hR4s"
      ],
          "source_type": "direct",
      "type": "rbac_group",
      "updated_at": "2024-10-30T23:58:27.427722Z"
    }
  ],
  "has_more": false,
  "next_page": "eyJjdXJzb3IiOiAicmJhY19ncm91cF8wMSJ9"
}
```

--------------------------------

### Install Go SDK (workaround)

Source: https://platform.claude.com/docs/pt-BR/build-with-claude/claude-in-microsoft-foundry

Install the standard Go SDK as a workaround since Foundry is not natively supported.

```bash
# O SDK Go ainda não oferece suporte nativo ao Foundry (consulte os exemplos de
# Autenticação para usar o SDK Go padrão como solução alternativa)
go get github.com/anthropics/anthropic-sdk-go
```

--------------------------------

### Quick start with advisor tool using Go

Source: https://platform.claude.com/docs/pt-BR/agents-and-tools/tool-use/advisor-tool

Use this Go code to create a message with the advisor tool. Requires the beta header 'advisor-tool-2026-03-01'. The example uses model 'claude-sonnet-5' as executor and 'claude-opus-5' as advisor.

```go
client := anthropic.NewClient()

response, err := client.Beta.Messages.New(context.TODO(), anthropic.BetaMessageNewParams{
	Model:     anthropic.ModelClaudeSonnet5,
	MaxTokens: 4096,
	Tools: []anthropic.BetaToolUnionParam{
		{OfAdvisorTool20260301: &anthropic.BetaAdvisorTool20260301Param{
			Model: anthropic.ModelClaudeOpus5,
		}},
	},
	Messages: []anthropic.BetaMessageParam{
		anthropic.NewBetaUserMessage(anthropic.NewBetaTextBlock("Build a concurrent worker pool in Go with graceful shutdown.")),
	},
	Betas: []anthropic.AnthropicBeta{
		anthropic.AnthropicBetaAdvisorTool2026_03_01,
	},
})
if err != nil {
	log.Fatal(err)
}
fmt.Println(response)
```

--------------------------------

### Quick start with advisor tool using CLI

Source: https://platform.claude.com/docs/pt-BR/agents-and-tools/tool-use/advisor-tool

Use this CLI command to create a message with the advisor tool. Requires the beta flag 'advisor-tool-2026-03-01'. The example uses model 'claude-sonnet-5' as executor and 'claude-opus-5' as advisor.

```bash
ant beta:messages create --beta advisor-tool-2026-03-01 <<'YAML'
model: claude-sonnet-5
max_tokens: 4096
tools:
  - type: advisor_20260301
    name: advisor
    model: claude-opus-5
messages:
  - role: user
    content: Build a concurrent worker pool in Go with graceful shutdown.
YAML
```

--------------------------------

### List and delete file resources from a session (cURL, CLI, Python, TypeScript, C#, Go)

Source: https://platform.claude.com/docs/pt-BR/managed-agents/files

Lists all resources of a session using resources.list and deletes a resource using resources.delete. The cURL example shows both list and delete commands. The CLI example shows the list and delete commands. The Python example lists and deletes. The TypeScript example lists and deletes, filtering out memory_store entries. The C# example lists and deletes. The Go example lists and deletes with error handling.

```bash
curl --fail-with-body -sS "${auth[@]}" \
  "${base_url}/sessions/${session_id}/resources" \
  | jq -r '.data[] | "\(.id) \(.type)"'

curl --fail-with-body -sS "${auth[@]}" -X DELETE \
  "${base_url}/sessions/${session_id}/resources/${resource_id}" >/dev/null
```

```bash
ant beta:sessions:resources list --session-id "$SESSION_ID"

ant beta:sessions:resources delete \
  --session-id "$SESSION_ID" \
  --resource-id "$RESOURCE_ID"
```

```python
listed = client.beta.sessions.resources.list(session.id)
for entry in listed.data:
    print(entry.id, entry.type)

client.beta.sessions.resources.delete(resource.id, session_id=session.id)
```

```typescript
const listed = await client.beta.sessions.resources.list(session.id);
for (const entry of listed.data) {
  if (entry.type !== "memory_store") {
    console.log(entry.id, entry.type);
  }
}

await client.beta.sessions.resources.delete(resource.id, {
  session_id: session.id,
});
```

```csharp
var listed = await client.Beta.Sessions.Resources.List(session.ID);
await foreach (var entry in listed.Paginate())
{
    var type = entry.Match<string>(repo => repo.Type, fileRes => fileRes.Type, memoryStore => memoryStore.Type);
    Console.WriteLine($"{entry.ID} {type}");
}

await client.Beta.Sessions.Resources.Delete(resource.ID, new() { SessionID = session.ID });
```

```go
listed, err := client.Beta.Sessions.Resources.List(ctx, session.ID, anthropic.BetaSessionResourceListParams{})
if err != nil {
	panic(err)
}
for _, entry := range listed.Data {
	fmt.Println(entry.ID, entry.Type)
}

if _, err := client.Beta.Sessions.Resources.Delete(ctx, resource.ID, anthropic.BetaSessionResourceDeleteParams{
	SessionID: session.ID,
}); err != nil {
	panic(err)
}
```

--------------------------------

### Install PHP SDK

Source: https://platform.claude.com/docs/pt-BR/build-with-claude/claude-in-microsoft-foundry

Install the Anthropic PHP SDK and Guzzle HTTP client.

```bash
composer require "anthropic-ai/sdk" "guzzlehttp/guzzle:^7"
```

--------------------------------

### Start services (macOS/Linux)

Source: https://platform.claude.com/docs/pt-BR/agents-and-tools/mcp-tunnels/quickstart

Starts the Docker Compose stack and checks logs for route and tunnel registration.

```bash
docker compose up -d
docker compose logs mcp-proxy | grep "route configured"
docker compose logs cloudflared | grep "Registered tunnel connection"
```

--------------------------------

### Install ant via Go

Source: https://platform.claude.com/docs/pt-BR/cli-sdks-libraries/cli/quickstart

Installs the `ant` CLI from source using `go install`. Requires Go 1.25 or later. The binary is placed in `$(go env GOPATH)/bin`.

```bash
go install github.com/anthropics/anthropic-cli/cmd/ant@latest
```

--------------------------------

### Get tunnel domain from Secret (kubectl)

Source: https://platform.claude.com/docs/pt-BR/agents-and-tools/mcp-tunnels/deploy-helm

Read the tunnel domain from the `mcp-tunnel` Secret after installation. The setup component stores the tunnel ID and domain in this Secret when `tunnel.id` is empty. Re-running the setup component reuses the stored tunnel ID and never creates a second tunnel.

```bash
kubectl -n mcp-tunnel get secret mcp-tunnel \
  -o jsonpath='{.data.tunnel-domain}' | base64 -d
```

--------------------------------

### Python: Criar quickstart.py

Source: https://platform.claude.com/docs/pt-BR/get-started

Cria o arquivo `quickstart.py` para o código do exemplo (o conteúdo não é exibido na página).

```text
Crie um arquivo chamado `quickstart.py`:

```

--------------------------------

### Install C# AWS SDK

Source: https://platform.claude.com/docs/pt-BR/build-with-claude/claude-platform-on-aws

Install the Anthropic C# SDK for AWS using dotnet.

```bash
dotnet add package Anthropic.Aws
```

--------------------------------

### Install MCP tunnel Helm chart (helm install)

Source: https://platform.claude.com/docs/pt-BR/agents-and-tools/mcp-tunnels/deploy-helm

Install the MCP tunnel Helm chart with the specified version and values file. The setup component runs as a Helm pre-install hook Job, so `helm install` blocks until it completes; on success the Job is deleted automatically. If `helm install` fails with a hook error, see the troubleshooting section on setup component authentication failures.

```bash
helm install mcp-tunnel \
  oci://us-docker.pkg.dev/anthropic-public-registry/charts/mcp-tunnel \
  --version 2.0.2 \
  --namespace mcp-tunnel --create-namespace \
  -f values.yaml
```

--------------------------------

### PHP: Run quickstart.php

Source: https://platform.claude.com/docs/pt-BR/get-started

Executes the PHP quickstart script.

```bash
php quickstart.php
```

--------------------------------

### Install Java AWS SDK (Gradle and Maven)

Source: https://platform.claude.com/docs/pt-BR/build-with-claude/claude-platform-on-aws

Install the Anthropic Java AWS SDK using Gradle or Maven. The Gradle example uses Kotlin DSL, and the Maven example uses XML.

```kotlin
implementation("com.anthropic:anthropic-java-aws:2.58.0")
```

```xml
<dependency>
  <groupId>com.anthropic</groupId>
  <artifactId>anthropic-java-aws</artifactId>
  <version>2.58.0</version>
</dependency>
```

--------------------------------

### Quick start: Create ClaudeLanguageModel and get a response

Source: https://platform.claude.com/docs/pt-BR/cli-sdks-libraries/libraries/apple-foundation-models#authentication

Create a ClaudeLanguageModel with an API key from the environment, start a session, and get a response. The model name is .sonnet5 and the API key is read from the ANTHROPIC_API_KEY environment variable.

```swift
import FoundationModels
import ClaudeForFoundationModels

let model = ClaudeLanguageModel(
  name: .sonnet5,
  auth: .apiKey(ProcessInfo.processInfo.environment["ANTHROPIC_API_KEY"] ?? "")
)

let session = LanguageModelSession(model: model)
let response = try await session.respond(to: "Plan a 4-day trip to Buenos Aires.")
print(response.content)
```

--------------------------------

### Response 200 Example for Get Connector Usage

Source: https://platform.claude.com/docs/pt-BR/api/beta/organization/analytics/connectors/list

Example response for the GET /v1/organizations/analytics/connectors endpoint. Shows the structure of the BetaConnectorUsage object with metrics for chat, Claude Code, cowork, and Office products, plus user and RBAC fields.

```json
{
  "data": [
    {
      "chat_metrics": {
        "distinct_conversation_connector_used_count": 0
      },
      "claude_code_metrics": {
        "distinct_session_connector_used_count": 0
      },
      "connector_name": "connector_name",
      "cowork_metrics": {
        "distinct_session_connector_used_count": 0
      },
      "distinct_user_count": 0,
      "office_metrics": {
        "excel": {
          "distinct_session_connector_used_count": 0
        },
        "outlook": {
          "distinct_session_connector_used_count": 0
        },
        "powerpoint": {
          "distinct_session_connector_used_count": 0
        },
        "word": {
          "distinct_session_connector_used_count": 0
        }
      },
      "connector_display_name": "connector_display_name",
      "individual_auth_distinct_user_count": 0,
      "managed_auth_distinct_user_count": 0,
      "product": "product",
      "rbac_group_id": "rbac_group_id",
      "rbac_group_name": "rbac_group_name",
      "read_call_count": 0,
      "unclassified_call_count": 0,
      "user_id": "user_id",
      "write_call_count": 0
    }
  ],
  "next_page": "next_page"
}
```

--------------------------------

### Java: Create QuickStart.java

Source: https://platform.claude.com/docs/pt-BR/get-started

Defines the main Java class for the quickstart. It uses the Anthropic Java SDK to send a message and print the response. Requires the SDK and Java 25.

```java
import com.anthropic.client.okhttp.AnthropicOkHttpClient;
import com.anthropic.models.messages.Message;
import com.anthropic.models.messages.MessageCreateParams;
import com.anthropic.models.messages.Model;

static void main() {
    var client = AnthropicOkHttpClient.fromEnv();

    var params = MessageCreateParams.builder()
        .model(Model.CLAUDE_OPUS_5)
        .maxTokens(1000)
        .addUserMessage(
            "What should I search for to find the latest developments in renewable energy?"
        )
        .build();

    Message message = client.messages().create(params);
    for (var block : message.content()) {
        block.text().ifPresent(textBlock -> IO.println(textBlock.text()));
    }
}
```

--------------------------------

### Ruby: Run quickstart.rb

Source: https://platform.claude.com/docs/pt-BR/get-started

Executes the Ruby quickstart script using bundle exec.

```bash
bundle exec ruby quickstart.rb
```

--------------------------------

### Maven: Compile and run QuickStart

Source: https://platform.claude.com/docs/pt-BR/get-started

Runs the QuickStart main class using Maven's exec plugin. This command compiles the project and executes the specified main class.

```bash
mvn compile exec:java -Dexec.mainClass=QuickStart
```

--------------------------------

### PHP: Create quickstart.php

Source: https://platform.claude.com/docs/pt-BR/get-started

Creates a PHP script that sends a message to the Claude model and prints the text response.

```php
<?php
require 'vendor/autoload.php';

use Anthropic\Client;
use Anthropic\Messages\Model;
use Anthropic\Messages\TextBlock;

$client = new Client();

$message = $client->messages->create(
    model: Model::CLAUDE_OPUS_5,
    maxTokens: 1000,
    messages: [
        [
            'role' => 'user',
            'content' => 'What should I search for to find the latest developments in renewable energy?',
        ],
    ],
);

foreach ($message->content as $block) {
    if ($block instanceof TextBlock) {
        echo $block->text . PHP_EOL;
    }
}
```

--------------------------------

### Response 200 example for get project details

Source: https://platform.claude.com/docs/pt-BR/api/compliance/apps/projects/retrieve

Example successful response (HTTP 200) from the GET /v1/compliance/apps/projects/{project_id} endpoint. Shows the project object with fields such as id, attachments_count, chats_count, created_at, deleted_at, description, instructions, is_private, name, organization_id, organization_uuid, updated_at, and user.

```json
{
  "id": "claude_proj_01Nm7PqRsTuVwXyZaBcDeFgH",
  "attachments_count": 3,
  "chats_count": 14,
  "created_at": "2025-03-12T18:22:41.123456Z",
  "deleted_at": "2019-12-27T18:11:19.117Z",
  "description": "Planning and research for the Q3 launch",
  "instructions": "Focus on concise, actionable answers.",
  "is_private": true,
  "name": "Q3 Product Launch",
  "organization_id": "org_015eofRkKpogX7uDKUyvBTph",
  "organization_uuid": "a1b2c3d4-e5f6-4789-a012-3456789abcde",
  "updated_at": "2025-03-14T09:05:17.456789Z",
  "user": {
    "id": "user_01WCz1FkmYMm4gnmykNKUu3Q",
    "email_address": "jane.doe@example.com"
  }
}
```

--------------------------------

### cURL request for Get Artifact Activity

Source: https://platform.claude.com/docs/pt-BR/api/beta/organization/analytics/artifacts/list

Sends a GET request to /v1/organizations/analytics/artifacts with the required anthropic-version header and API key. No query parameters are included in this example.

```bash
curl https://api.anthropic.com/v1/organizations/analytics/artifacts \
    -H 'anthropic-version: 2023-06-01' \
    -H "X-Api-Key: $ANTHROPIC_API_KEY"
```

--------------------------------

### Executar o exemplo Python

Source: https://platform.claude.com/docs/pt-BR/get-started

Executa o arquivo quickstart.py que contém o código de exemplo Python. A saída esperada é uma lista de estratégias de busca para encontrar desenvolvimentos recentes em energia renovável.

```bash
python quickstart.py
```

```text
Here are some effective search strategies to find the latest developments in renewable energy:

## General Search Terms
- "Renewable energy news 2025"
- ...
```

--------------------------------

### Response 200 for get current organization

Source: https://platform.claude.com/docs/pt-BR/api/admin-api/organization/get-me

Example successful response from the GET /v1/organizations/me endpoint, showing the organization object with id, name, and type fields.

```json
{
  "id": "12345678-1234-5678-1234-567812345678",
  "name": "Organization Name",
  "type": "organization"
}
```

--------------------------------

### GET /v1/organizations/analytics/plugins

Source: https://platform.claude.com/docs/pt-BR/api/admin/analytics

Retrieves per-plugin install and invocation usage for a given day, with pagination.

```APIDOC
## GET /v1/organizations/analytics/plugins

### Description
Get per-plugin install + invocation usage for a given day, with pagination.

### Method
GET

### Endpoint
/v1/organizations/analytics/plugins

### Parameters
#### Query Parameters
- **date** (string) - Required - The day for which to retrieve usage.
- **cursor** (string) - Optional - Cursor for pagination.

### Response
#### Success Response (200)
- **plugins** (array) - List of plugin usage objects.
- **next_cursor** (string) - Cursor for the next page.

#### Response Example
{
  "plugins": [
    {
      "plugin_id": "plugin_123",
      "install_count": 2,
      "invocation_count": 10
    }
  ],
  "next_cursor": "cursor_abc"
}
```

--------------------------------

### Java: Create project directory

Source: https://platform.claude.com/docs/pt-BR/get-started

Creates the directory structure for a Java quickstart project. Requires JDK 25 or later and Gradle or Maven on the PATH.

```bash
mkdir -p claude-quickstart/src/main/java && cd claude-quickstart
```

--------------------------------

### Ruby: Create project and install SDK

Source: https://platform.claude.com/docs/pt-BR/get-started

Creates a new directory, initializes a Ruby bundle, and adds the anthropic gem.

```bash
mkdir claude-quickstart && cd claude-quickstart
bundle init
bundle add anthropic
```

--------------------------------

### Ruby: Create quickstart.rb

Source: https://platform.claude.com/docs/pt-BR/get-started

Creates a Ruby script that sends a message to the Claude model and prints the text response.

```ruby
require "anthropic"

client = Anthropic::Client.new

message = client.messages.create(
  model: Anthropic::Model::CLAUDE_OPUS_5,
  max_tokens: 1000,
  messages: [
    {
      role: "user",
      content: "What should I search for to find the latest developments in renewable energy?"
    }
  ]
)

message.content.each do |block|
  puts block.text if block.type == :text
end
```

--------------------------------

### GET /v1/organizations/rbac_groups/{group_id}

Source: https://platform.claude.com/docs/pt-BR/api/http/beta/organization/rbac_groups/retrieve

This snippet documents the GET endpoint to retrieve an RBAC Group by its ID. It includes the path parameter, request example, and the full response schema with a sample response.

```APIDOC
## GET /v1/organizations/rbac_groups/{group_id}

### Description
Retrieve an RBAC Group by ID. The RBAC Groups API is available to Claude Enterprise organizations only.

### Method
GET

### Endpoint
/v1/organizations/rbac_groups/{group_id}

### Parameters
#### Path Parameters
- **group_id** (string) - Required - ID of the RBAC Group.

### Request Example
```
curl https://api.anthropic.com/v1/organizations/rbac_groups/$GROUP_ID \
    -H 'anthropic-version: 2023-06-01' \
    -H "X-Api-Key: $ANTHROPIC_API_KEY"
```

### Response
#### Success Response (200)
- **type** (string) - Object type. For RBAC Groups, this is always `"rbac_group"`.
- **id** (string) - ID of the RBAC Group.
- **created_at** (string) - RFC 3339 timestamp of when the RBAC Group was created.
- **name** (string) - Name of the RBAC Group. Not uniqueness-enforced.
- **roles** (array of string or null) - RBAC Role IDs attached to this RBAC Group. Role attachment is managed in the admin settings and is read-only on this API. `null` means role data was temporarily unavailable — retry to distinguish from an empty list.
- **source_type** (string) - How the RBAC Group was created: `"direct"` for groups created directly (for example, in the organization's admin settings), `"scim"` for groups provisioned by the identity provider.
- **updated_at** (string) - RFC 3339 timestamp of when the RBAC Group was last updated.

#### Response Example
```
{
  "id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF",
  "created_at": "2024-10-30T23:58:27.427722Z",
  "name": "Engineering",
  "roles": [
    "rbac_role_016J8xVtKpDq3Wy9ZmN2hR4s"
  ],
  "source_type": "direct",
  "type": "rbac_group",
  "updated_at": "2024-10-30T23:58:27.427722Z"
}
```
```

--------------------------------

### Configurar cliente com fromEnv()

Source: https://platform.claude.com/docs/pt-BR/cli-sdks-libraries/sdks/java

Configura o cliente usando propriedades do sistema ou variáveis de ambiente. As propriedades do sistema têm precedência sobre as variáveis de ambiente.

```java
import com.anthropic.client.AnthropicClient;
import com.anthropic.client.okhttp.AnthropicOkHttpClient;

// Configura usando as propriedades de sistema `anthropic.apiKey`, `anthropic.authToken` e `anthropic.baseUrl`
// Ou configura usando as variáveis de ambiente `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN` e `ANTHROPIC_BASE_URL`
AnthropicClient client = AnthropicOkHttpClient.fromEnv();
```

--------------------------------

### GET /v1/organizations/workspaces/{workspace_id}/rate_limits

Source: https://platform.claude.com/docs/pt-BR/api/admin/workspaces/rate_limits/list

This snippet documents the GET endpoint for listing workspace rate limit overrides, including path and query parameters, request example, and response schema.

```APIDOC
## GET /v1/organizations/workspaces/{workspace_id}/rate_limits

### Description
List the rate limit overrides configured for a workspace. Returns only the groups and limiter types that have an override at the workspace level. Groups without overrides inherit the organization limits and are not listed; use `GET /v1/organizations/rate_limits` to see them.

### Method
GET

### Endpoint
/v1/organizations/workspaces/{workspace_id}/rate_limits

### Parameters
#### Path Parameters
- **workspace_id** (string) - Required - The ID of the workspace.

#### Query Parameters
- **group_type** (string) - Optional - Filter by group type. One of: "batch", "files", "model_group", "skills", "token_count", "web_search".
- **limit** (number) - Optional - Maximum number of items to return per page. Ranges from `1` to `1000`. When omitted, every remaining entry is returned in a single page and `next_page` is `null`.
- **page** (string) - Optional - Opaque cursor from a previous response's `next_page`.

### Request Example
```
curl https://api.anthropic.com/v1/organizations/workspaces/$WORKSPACE_ID/rate_limits \
    -H 'anthropic-version: 2023-06-01' \
    -H "X-Api-Key: $ANTHROPIC_API_KEY"
```

### Response
#### Success Response (200)
- **data** (array of BetaWorkspaceRateLimit) - Rate-limit entries for the workspace, one per group that has at least one override.
  - **type** (string) - Object type. Always `workspace_rate_limit` for workspace rate-limit entries.
  - **group_type** (string) - The kind of rate-limit group this entry represents. `model_group` entries apply to a family of models (listed in `models`); other values apply to an API-surface category and have `models` set to `null`. One of: "batch", "files", "model_group", "skills", "token_count", "web_search".
  - **limits** (array of BetaWorkspaceRateLimitValue) - The limiter values overridden for this group in this workspace. Limiter types without a workspace override are omitted and inherit the organization value.
    - **type** (string) - The limiter type (for example, `requests_per_minute` or `input_tokens_per_minute`).
    - **org_limit** (number or null) - The organization-level value for the same limiter type, for reference. `null` when the organization has no limit configured for this limiter type.
    - **value** (number) - The workspace-level override value for this limiter type.
  - **models** (array of string or null) - Model names this entry's limits apply to, including aliases. `null` when `group_type` is not `"model_group"`.
  - **rate_limit_id** (string) - The `id` of the RateLimit group this override applies to.
  - **workspace_id** (string) - ID of the Workspace this override applies to.
- **next_page** (string or null) - Opaque cursor for the next page of results, or `null` when no entries remain beyond this response.

#### Response Example
```
{
  "data": [
    {
      "group_type": "batch",
      "limits": [
        {
          "org_limit": 0,
          "type": "type",
          "value": 0
        }
      ],
      "models": [
        "string"
      ],
      "rate_limit_id": "rate_limit_id",
      "type": "workspace_rate_limit",
      "workspace_id": "workspace_id"
    }
  ],
  "next_page": "next_page"
}
```
```

--------------------------------

### Get RBAC Role - Response 200

Source: https://platform.claude.com/docs/pt-BR/api/admin/rbac_roles/retrieve

Example successful response from the Get RBAC Role endpoint, returning a BetaRBACRole object with fields: id, created_at, name, type, and updated_at.

```json
{
  "id": "rbac_role_016J8xVtKpDq3Wy9ZmN2hR4s",
  "created_at": "2024-10-30T23:58:27.427722Z",
  "name": "Project Editor",
  "type": "rbac_role",
  "updated_at": "2024-10-30T23:58:27.427722Z"
}
```

--------------------------------

### Create hello_server.py (macOS/Linux)

Source: https://platform.claude.com/docs/pt-BR/agents-and-tools/mcp-tunnels/quickstart

Creates a simple MCP server with a hello tool. Uses a here-document to write the file.

```bash
cat > hello_server.py <<'EOF'
from mcp.server.fastmcp import FastMCP

mcp = FastMCP("hello")


@mcp.tool()
def hello(name: str = "world") -> str:
    """Say hello to someone."""
    return f"Hello, {name}!"


if __name__ == "__main__":
    mcp.run(transport="streamable-http")
EOF
```

--------------------------------

### Get Activity Summaries Response 200

Source: https://platform.claude.com/docs/pt-BR/api/beta/organization/analytics/retrieve_summaries

Example 200 response for GET /v1/organizations/analytics/summaries. Contains a summaries array with per-day activity metrics such as active user counts, adoption rates, and seat counts.

```json
{
  "summaries": [
    {
      "assigned_seat_count": 0,
      "cowork_daily_active_user_count": 0,
      "cowork_monthly_active_user_count": 0,
      "cowork_weekly_active_user_count": 0,
      "daily_active_user_count": 0,
      "daily_adoption_rate": 0,
      "ending_at": "2019-12-27T18:11:19.117Z",
      "monthly_active_user_count": 0,
      "monthly_adoption_rate": 0,
      "pending_invite_count": 0,
      "starting_at": "2019-12-27T18:11:19.117Z",
      "weekly_active_user_count": 0,
      "weekly_adoption_rate": 0,
      "chat_daily_active_user_count": 0,
      "chat_monthly_active_user_count": 0,
      "chat_weekly_active_user_count": 0,
      "claude_code_daily_active_user_count": 0,
      "claude_code_monthly_active_user_count": 0,
      "claude_code_weekly_active_user_count": 0,
      "claude_design_daily_active_user_count": 0,
      "claude_design_monthly_active_user_count": 0,
      "claude_design_weekly_active_user_count": 0,
      "office_agent_daily_active_user_count": 0,
      "office_agent_monthly_active_user_count": 0,
      "office_agent_weekly_active_user_count": 0,
      "science_daily_active_user_count": 0,
      "science_entitled_user_count": 0,
      "science_monthly_active_user_count": 0,
      "science_weekly_active_user_count": 0
    }
  ]
}
```

--------------------------------

### Response 200 for GET /v1/organizations/analytics/plugins

Source: https://platform.claude.com/docs/pt-BR/api/beta/organization/analytics/plugins/list

Example 200 response showing the BetaPluginUsage object with plugin metrics and pagination.

```json
{
  "data": [
    {
      "claude_code_metrics": {
        "distinct_session_plugin_used_count": 0
      },
      "cowork_metrics": {
        "distinct_session_plugin_used_count": 0
      },
      "distinct_user_count": 0,
      "install_count": 0,
      "invocation_count": 0,
      "plugin_name": "plugin_name",
      "plugin_id": "plugin_id",
      "product": "product",
      "rbac_group_id": "rbac_group_id",
      "rbac_group_name": "rbac_group_name",
      "user_id": "user_id"
    }
  ],
  "next_page": "next_page"
}
```

--------------------------------

### Progress notes example (progress.txt)

Source: https://platform.claude.com/docs/pt-BR/build-with-claude/prompt-engineering/claude-prompting-best-practices

Unstructured text format for tracking progress across sessions, including notes on fixes and next steps.

```text
// Progress notes (progress.txt)
Session 3 progress:
- Fixed authentication token validation
- Updated user model to handle edge cases
- Next: investigate user_management test failures (test #2)
- Note: Do not remove tests as this could lead to missing functionality
```

--------------------------------

### SKILL.md instructions with pdfplumber example

Source: https://platform.claude.com/docs/pt-BR/agents-and-tools/agent-skills/overview

Main body of a SKILL.md file containing procedural knowledge. It includes a quick start section with a Python example using pdfplumber to extract text from a PDF, and a link to FORMS.md for advanced form filling.

```markdown
# PDF Processing

## Quick start

Use pdfplumber to extract text from PDFs:

```python
import pdfplumber

with pdfplumber.open("document.pdf") as pdf:
    text = pdf.pages[0].extract_text()
```

For advanced form filling, see [FORMS.md](FORMS.md).
```

--------------------------------

### Instalar helpers MCP em Go

Source: https://platform.claude.com/docs/pt-BR/agents-and-tools/mcp-connector

Obtém o subpacote `mcp` do SDK Go, que se baseia no MCP Go SDK.

```bash
go get github.com/anthropics/anthropic-sdk-go/mcp
```

--------------------------------

### GET /v1/organizations/analytics/plugins

Source: https://platform.claude.com/docs/pt-BR/api/beta/organization/analytics/plugins/list

Retrieves per-plugin install and invocation usage for a given day or date range, with pagination and optional grouping and filtering.

```APIDOC
## GET /v1/organizations/analytics/plugins

### Description
Get per-plugin install + invocation usage for a given day, with pagination. Returns plugin usage metrics for the organization across Cowork and Claude Code, sorted by plugin name. The `plugin_name` value `third-party` is an aggregate bucket, not a plugin: it collects plugin activity, from either surface, for which the reporting client did not provide a plugin name — so an organization's own plugins can contribute both to their own named rows and to this bucket. Use `group_by[]` to break usage out per member, per RBAC group, or per product surface (Cowork / Claude Code), and `filter[]` to scope results; the parameter descriptions list the supported dimensions. Requires an API key with the `read:analytics` scope. `starting_date` / `ending_date` select range-rollup mode like `/skills`.

### Method
GET

### Endpoint
/v1/organizations/analytics/plugins

### Parameters
#### Query Parameters
- **date** (string) - Optional - UTC date in YYYY-MM-DD format. The day to get plugin usage for. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01.
- **ending_date** (string) - Optional - UTC date in YYYY-MM-DD format. End of the date range (exclusive); only valid with `starting_date`. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day), so this can be at most today — which is also the default when omitted, resolved once when the first page is served and reused for the rest of the pagination sequence. At most 366 days after `starting_date`.
- **filter** (array of string) - Optional - Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint: `plugin_name`, `product`, `rbac_group_id`, `user_id`. Value forms: `plugin_name` matches case-insensitively; `product` is `claude_code` or `cowork` (the only surfaces with plugin attribution); `rbac_group_id` takes the tagged id (`rbac_group_...`, as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each covered UTC day (time-of-usage attribution); `user_id` takes a tagged user id (`user_...`), as emitted in responses. An unsupported dimension returns 400. At most 100 entries.
- **group_by** (array of "product" or "rbac_group_id" or "user_id") - Optional - Dimensions to break results out by (e.g. `group_by[]=user_id`). Supported on this endpoint: `product`, `rbac_group_id`, `user_id`. On this endpoint `product` takes the values `claude_code` or `cowork` only (the surfaces with plugin attribution). Grouped rows carry the requested dimension values as additional fields and paginate like ungrouped responses via `next_page`; an unsupported dimension returns 400. `rbac_group_id` attributes a user to every group they held at any point during each covered UTC day, so grouped rows are not an exclusive partition and can sum above org-level totals. At most 100 entries.
- **limit** (number) - Optional - Number of results per page (1-1000, default 100).
- **order** ("asc" or "desc") - Optional - Sort direction: `asc` or `desc`. Defaults to `asc` for the endpoint's sort column and to `desc` when `order_by` names a metric (a top-N ranking). Applies to `order_by`, or to the endpoint's default sort field when `order_by` is omitted.
- **order_by** (string) - Optional - Sort field. Restricted to the endpoint's sort column plus its rankable metrics (metrics default to descending; a few metrics rank in date-range mode only, per the endpoint's documented orderable set).
- **page** (string) - Optional - Opaque cursor from a previous response's `next_page` field.
- **starting_date** (string) - Optional - UTC date in YYYY-MM-DD format. Start of a date range (inclusive). Enables rollup mode: one row per entity aggregated over the whole range — addable counters are summed across days, and a distinct count is never summed where summing could double-count (a field's range value is recomputed exactly over the window, approximate via HLL with typical error under 2%, null, or — for the creation-event counts, whose per-day values cannot overlap — a per-day sum that is itself exact; each field's own description says which). Use either `date` or `starting_date`, not both. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01.

### Request Example
No request body is required for this endpoint.

### Response
#### Success Response (200)
The response contains plugin usage metrics, including pagination via `next_page`. Specific response fields are not documented in the source.

#### Response Example
No response example is provided in the source.

```

--------------------------------

### Response 200 for Get Cost Report

Source: https://platform.claude.com/docs/pt-BR/api/admin-api/usage-cost/get-cost-report

Example JSON response from the Get Cost Report endpoint. It shows a data array with cost results, including fields like amount, model, and workspace_id, plus pagination fields has_more and next_page.

```json
{
  "data": [
    {
      "ending_at": "2025-08-02T00:00:00Z",
      "results": [
        {
          "amount": "123.78912",
          "context_window": "0-200k",
          "cost_type": "tokens",
          "currency": "USD",
          "description": "Claude Opus 5 Usage - Input Tokens",
          "inference_geo": "global",
          "model": "claude-opus-5",
          "service_tier": "standard",
          "token_type": "uncached_input_tokens",
          "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ"
        }
      ],
      "starting_at": "2025-08-01T00:00:00Z"
    }
  ],
  "has_more": true,
  "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo="
}
```

--------------------------------

### Go quickstart: Use OpenAI SDK with Claude

Source: https://platform.claude.com/docs/pt-BR/cli-sdks-libraries/libraries/openai-sdk

Configure the OpenAI client with your Anthropic API key and base URL, then call the chat completions endpoint with the claude-opus-5 model.

```go
package main

import (
	"context"
	"fmt"
	"os"

	"github.com/openai/openai-go/v3"
	"github.com/openai/openai-go/v3/option"
)

func main() {
	client := openai.NewClient(
		option.WithAPIKey(os.Getenv("ANTHROPIC_API_KEY")),   // Your Claude API key
		option.WithBaseURL("https://api.anthropic.com/v1/"), // the Claude API endpoint
	)

	response, err := client.Chat.Completions.New(context.Background(), openai.ChatCompletionNewParams{
		Model: "claude-opus-5", // Claude model name
		Messages: []openai.ChatCompletionMessageParamUnion{
			openai.SystemMessage("You are a helpful assistant."),
			openai.UserMessage("Who are you?"),
		},
	})
	if err != nil {
		panic(err)
	}

	fmt.Println(response.Choices[0].Message.Content)
}
```

--------------------------------

### Tool definition for get_stock_price

Source: https://platform.claude.com/docs/pt-BR/api/beta/messages/count_tokens

Example of a tools array with a single tool definition for getting stock prices, including input schema with required ticker.

```json
[
  {
    "name": "get_stock_price",
    "description": "Get the current stock price for a given ticker symbol.",
    "input_schema": {
      "type": "object",
      "properties": {
        "ticker": {
          "type": "string",
          "description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
        }
      },
      "required": ["ticker"]
    }
  }
]
```

--------------------------------

### Executar o componente de setup

Source: https://platform.claude.com/docs/pt-BR/agents-and-tools/mcp-tunnels/deploy-compose

Executa o componente de setup via Docker Compose. O comando é idempotente e reutiliza o ID do túnel e a CA existentes.

```bash
docker compose run --rm setup
```

--------------------------------

### Instalar SDK C# para Vertex

Source: https://platform.claude.com/docs/pt-BR/build-with-claude/claude-on-vertex-ai

Adiciona o pacote Anthropic.Vertex via dotnet.

```bash
dotnet add package Anthropic.Vertex
```

--------------------------------

### GET /v1/organizations/analytics/plugins

Source: https://platform.claude.com/docs/pt-BR/api/http/beta/organization/analytics/plugins

Retrieves per-plugin install and invocation usage for a given day, with pagination. Returns a BetaPluginUsage object containing the usage data and a pagination token.

```APIDOC
## GET /v1/organizations/analytics/plugins

### Description
Get per-plugin install + invocation usage for a given day, with pagination.

### Method
GET

### Endpoint
/v1/organizations/analytics/plugins

### Response
#### Success Response (200)
- **data** (array) - The usage data for each plugin.
- **next_page** (string) - Pagination token for the next page of results.

#### Response Example
{
  "data": [],
  "next_page": "string"
}
```

--------------------------------

### Go: Define get_weather tool with InputExamples

Source: https://platform.claude.com/docs/pt-BR/agents-and-tools/tool-use/define-tools

Creates an Anthropic client and sends a message with a 'get_weather' tool definition, using InputSchema and InputExamples. The example shows how to use map[string]any for properties and demonstrate optional 'unit' by omitting it in an input example.

```Go
client := anthropic.NewClient()

response, err := client.Messages.New(context.TODO(), anthropic.MessageNewParams{
	Model:     anthropic.ModelClaudeOpus5,
	MaxTokens: 1024,
	Tools: []anthropic.ToolUnionParam{
		{Of: &anthropic.ToolParam{
			Name:        "get_weather",
			Description: anthropic.String("Get the current weather in a given location"),
			InputSchema: anthropic.ToolInputSchemaParam{
				Properties: map[string]any{
					"location": map[string]any{
						"type":        "string",
						"description": "The city and state, e.g. San Francisco, CA",
					},
					"unit": map[string]any{
						"type":        "string",
						"enum":        []string{"celsius", "fahrenheit"},
						"description": "The unit of temperature",
					},
				},
				Required: []string{"location"},
			},
			InputExamples: []map[string]any{
				{
					"location": "San Francisco, CA",
					"unit":     "fahrenheit",
				},
				{
					"location": "Tokyo, Japan",
					"unit":     "celsius",
				},
				{
					"location": "New York, NY",
					// Demonstra que 'unit' é opcional
				},
			},
		}},
	},
	Messages: []anthropic.MessageParam{
		anthropic.NewUserMessage(anthropic.NewTextBlock("What's the weather like in San Francisco?")),
	},
})
if err != nil {
	log.Fatal(err)
}
fmt.Println(response.RawJSON())
```

--------------------------------

### Get Messages Usage Report - Response 200

Source: https://platform.claude.com/docs/pt-BR/api/admin-api/usage-cost/get-messages-usage-report

Example 200 response from the Get Messages Usage Report endpoint. The response contains a data array with usage details per workspace, including token counts, model, and service tier, plus pagination fields has_more and next_page.

```json
{
  "data": [
    {
      "ending_at": "2025-08-02T00:00:00Z",
      "results": [
        {
          "account_id": "user_01WCz1FkmYMm4gnmykNKUu3Q",
          "api_key_id": "apikey_01Rj2N8SVvo6BePZj99NhmiT",
          "cache_creation": {
            "ephemeral_1h_input_tokens": 0,
            "ephemeral_5m_input_tokens": 0
          },
          "cache_read_input_tokens": 200,
          "context_window": "0-200k",
          "inference_geo": "global",
          "model": "claude-opus-5",
          "output_tokens": 500,
          "server_tool_use": {
            "web_search_requests": 10
          },
          "service_account_id": "svac_01Hk3R9TWxq7CfQak00OiVw4",
          "service_tier": "standard",
          "uncached_input_tokens": 1500,
          "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ"
        }
      ],
      "starting_at": "2025-08-01T00:00:00Z"
    }
  ],
  "has_more": true,
  "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo="
}
```

--------------------------------

### Instalar o SDK com extras para plataformas e aiohttp

Source: https://platform.claude.com/docs/pt-BR/cli-sdks-libraries/sdks/python

Instala o SDK com extras para integrações específicas de plataforma ou melhor desempenho assíncrono. O suporte ao Microsoft Foundry está incluído no pacote base.

```bash
# Para suporte ao Amazon Bedrock
pip install "anthropic[bedrock]"

# Para suporte ao Google Cloud
pip install "anthropic[vertex]"

# Para suporte ao Claude Platform na AWS
pip install "anthropic[aws]"

# O suporte ao Microsoft Foundry está incluído no pacote base

# Para melhor desempenho assíncrono com aiohttp
pip install "anthropic[aiohttp]"
```

--------------------------------

### Instalar SDK Go para Vertex

Source: https://platform.claude.com/docs/pt-BR/build-with-claude/claude-on-vertex-ai

Obtém o SDK da Anthropic para Go via go get.

```bash
go get github.com/anthropics/anthropic-sdk-go
```

--------------------------------

### Criar projeto e instalar SDK Go

Source: https://platform.claude.com/docs/pt-BR/get-started

Cria um novo módulo e adiciona o SDK da Anthropic para Go.

```bash
mkdir claude-quickstart && cd claude-quickstart
go mod init claude-quickstart
go get github.com/anthropics/anthropic-sdk-go
```