new_relic-automation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

New Relic Automation via Rube MCP

通过Rube MCP实现New Relic自动化

Automate New Relic operations through Composio's New Relic toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/new_relic

通过Composio的New Relic工具包，借助Rube MCP自动化New Relic操作。

工具包文档：composio.dev/toolkits/new_relic

Prerequisites

前提条件

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active New Relic connection via
```
RUBE_MANAGE_CONNECTIONS
```
with toolkit
```
new_relic
```
Always call
```
RUBE_SEARCH_TOOLS
```
first to get current tool schemas

必须已连接Rube MCP（需具备RUBE_SEARCH_TOOLS权限）
通过
```
RUBE_MANAGE_CONNECTIONS
```
并使用工具包
```
new_relic
```
建立有效的New Relic连接
请始终先调用
```
RUBE_SEARCH_TOOLS
```
以获取最新的工具架构

Setup

设置步骤

Get Rube MCP: Add

https://rube.app/mcp

as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

Verify Rube MCP is available by confirming
```
RUBE_SEARCH_TOOLS
```
responds
Call
```
RUBE_MANAGE_CONNECTIONS
```
with toolkit
```
new_relic
```
If connection is not ACTIVE, follow the returned auth link to complete setup
Confirm connection status shows ACTIVE before running any workflows

获取Rube MCP：在客户端配置中添加

https://rube.app/mcp

作为MCP服务器。无需API密钥——只需添加该端点即可使用。

通过确认
```
RUBE_SEARCH_TOOLS
```
能正常响应，验证Rube MCP是否可用
调用
```
RUBE_MANAGE_CONNECTIONS
```
并指定工具包
```
new_relic
```
如果连接状态未显示为ACTIVE，请按照返回的认证链接完成设置
在运行任何工作流之前，确认连接状态为ACTIVE

Tool Discovery

工具发现

Always discover available tools before executing workflows:

RUBE_SEARCH_TOOLS: queries=[{"use_case": "APM, alerts, dashboards, NRQL queries, and infrastructure monitoring", "known_fields": ""}]

This returns:

Available tool slugs for New Relic
Recommended execution plan steps
Known pitfalls and edge cases
Input schemas for each tool

在执行工作流之前，请始终先发现可用工具：

RUBE_SEARCH_TOOLS: queries=[{"use_case": "APM, alerts, dashboards, NRQL queries, and infrastructure monitoring", "known_fields": ""}]

该调用将返回：

New Relic的可用工具标识（slug）
推荐的执行计划步骤
已知的陷阱和边缘情况
每个工具的输入架构

Core Workflows

核心工作流

1. Discover Available New Relic Tools

1. 发现可用的New Relic工具

RUBE_SEARCH_TOOLS:
  queries:
    - use_case: "list all available New Relic tools and capabilities"

Review the returned tools, their descriptions, and input schemas before proceeding.

RUBE_SEARCH_TOOLS:
  queries:
    - use_case: "list all available New Relic tools and capabilities"

在继续操作之前，请查看返回的工具、其描述以及输入架构。

2. Execute New Relic Operations

2. 执行New Relic操作

After discovering tools, execute them via:

RUBE_MULTI_EXECUTE_TOOL:
  tools:
    - tool_slug: "<discovered_tool_slug>"
      arguments: {<schema-compliant arguments>}
  memory: {}
  sync_response_to_workbench: false

发现工具后，通过以下方式执行：

RUBE_MULTI_EXECUTE_TOOL:
  tools:
    - tool_slug: "<discovered_tool_slug>"
      arguments: {<schema-compliant arguments>}
  memory: {}
  sync_response_to_workbench: false

3. Multi-Step Workflows

3. 多步骤工作流

For complex workflows involving multiple New Relic operations:

Search for all relevant tools:
```
RUBE_SEARCH_TOOLS
```
with specific use case
Execute prerequisite steps first (e.g., fetch before update)
Pass data between steps using tool responses
Use
```
RUBE_REMOTE_WORKBENCH
```
for bulk operations or data processing

对于涉及多个New Relic操作的复杂工作流：

使用特定用例调用
```
RUBE_SEARCH_TOOLS
```
，搜索所有相关工具
先执行前置步骤（例如，先获取数据再更新）
通过工具响应在步骤之间传递数据
使用
```
RUBE_REMOTE_WORKBENCH
```
进行批量操作或数据处理

Common Patterns

常见模式

Search Before Action

操作前先搜索

Always search for existing resources before creating new ones to avoid duplicates.

在创建新资源之前，请始终先搜索现有资源以避免重复。

Pagination

分页

Many list operations support pagination. Check responses for

next_cursor

page_token

and continue fetching until exhausted.

许多列表操作支持分页。检查响应中的

next_cursor

或

page_token

，并持续获取数据直到全部获取完成。

Error Handling

错误处理

Check tool responses for errors before proceeding
If a tool fails, verify the connection is still ACTIVE
Re-authenticate via
```
RUBE_MANAGE_CONNECTIONS
```
if connection expired

在继续操作之前，检查工具响应是否存在错误
如果工具执行失败，请验证连接是否仍处于ACTIVE状态
如果连接过期，请通过
```
RUBE_MANAGE_CONNECTIONS
```
重新认证

Batch Operations

批量操作

For bulk operations, use

RUBE_REMOTE_WORKBENCH

with

run_composio_tool()

in a loop with

ThreadPoolExecutor

for parallel execution.

对于批量操作，使用

RUBE_REMOTE_WORKBENCH

，结合

ThreadPoolExecutor

在循环中调用

run_composio_tool()

以实现并行执行。

Known Pitfalls

已知陷阱

Always search tools first: Tool schemas and available operations may change. Never hardcode tool slugs without first discovering them via
```
RUBE_SEARCH_TOOLS
```
.
Check connection status: Ensure the New Relic connection is ACTIVE before executing any tools. Expired OAuth tokens require re-authentication.
Respect rate limits: If you receive rate limit errors, reduce request frequency and implement backoff.
Validate schemas: Always pass strictly schema-compliant arguments. Use
```
RUBE_GET_TOOL_SCHEMAS
```
to load full input schemas when
```
schemaRef
```
is returned instead of
```
input_schema
```
.

始终先搜索工具：工具架构和可用操作可能会发生变化。在未通过
```
RUBE_SEARCH_TOOLS
```
发现工具标识（slug）之前，切勿硬编码工具标识。
检查连接状态：在执行任何工具之前，请确保New Relic连接处于ACTIVE状态。过期的OAuth令牌需要重新认证。
遵守速率限制：如果收到速率限制错误，请降低请求频率并实现退避机制。
验证架构：请始终传递严格符合架构要求的参数。当返回的是
```
schemaRef
```
而非
```
input_schema
```
时，使用
```
RUBE_GET_TOOL_SCHEMAS
```
加载完整的输入架构。

Quick Reference

快速参考

Operation	Approach
Find tools	`RUBE_SEARCH_TOOLS` with New Relic-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `new_relic`
Execute	`RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs
Bulk ops	`RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`
Full schema	`RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef`

Toolkit docs: composio.dev/toolkits/new_relic

操作	方法
查找工具	使用New Relic特定用例调用 `RUBE_SEARCH_TOOLS`
建立连接	使用工具包 `new_relic` 调用 `RUBE_MANAGE_CONNECTIONS`
执行操作	使用发现的工具标识调用 `RUBE_MULTI_EXECUTE_TOOL`
批量操作	在 `RUBE_REMOTE_WORKBENCH` 中使用 `run_composio_tool()`
获取完整架构	对带有 `schemaRef` 的工具调用 `RUBE_GET_TOOL_SCHEMAS`

工具包文档：composio.dev/toolkits/new_relic