Rollbar MCP Server

Rollbar MCP Server

Enables AI assistants to interact with Rollbar error tracking and monitoring service, allowing them to diagnose issues, view item details, list deployments, retrieve session replays, and update item properties through natural language commands.

Category
访问服务器

README

rollbar-mcp-server

A Model Context Protocol (MCP) server for Rollbar.

Features

This MCP server implementes the stdio server type, which means your AI tool (e.g. Claude) will run it directly; you don't run a separate process or connect over http.

Configuration

  • ROLLBAR_ACCESS_TOKEN: an access token for your Rollbar project with read and/or write scope.
  • ROLLBAR_API_BASE (optional): override the Rollbar API base URL (defaults to https://api.rollbar.com/api/1). Use this when running against a staging or development Rollbar deployment.

Tools

get-item-details(counter, max_tokens?): Given an item number, fetch the item details and last occurrence details. Supports an optional max_tokens parameter (default: 20000) to automatically truncate large occurrence responses. Example prompt: Diagnose the root cause of Rollbar item #123456

get-deployments(limit): List deploy data for the given project. Example prompt: List the last 5 deployments or Are there any failed deployments?

get-version(version, environment): Fetch version details for the given version string, environment name, and the configured project.

get-top-items(environment): Fetch the top items in the last 24 hours given the environment name, and the configured project.

list-items(environment): List items filtered by status, environment and a search query.

get-replay(environment, sessionId, replayId, delivery?): Retrieve session replay metadata and payload for a specific session in the configured project. By default the tool writes the replay JSON to a temporary file (under your system temp directory) and returns the path so any client can inspect it. Set delivery="resource" to receive a rollbar://replay/<environment>/<sessionId>/<replayId> link for MCP-aware clients. Example prompt: Fetch the replay 789 from session abc in staging.

update-item(itemId, status?, level?, title?, assignedUserId?, resolvedInVersion?, snoozed?, teamId?): Update an item's properties including status, level, title, assignment, and more. Example prompt: Mark Rollbar item #123456 as resolved or Assign item #123456 to user ID 789. (Requires write scope)

How to Use

Tested with node 20 and 22 (nvm use 22).

Claude Code

Configure your .mcp.json as follows:

{
  "mcpServers": {
    "rollbar": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@rollbar/mcp-server@latest"
      ],
      "env": {
        "ROLLBAR_ACCESS_TOKEN": "<project read/write access token>"
      }
    }
  }
}

Optionally include ROLLBAR_API_BASE in the env block to target a non-production API endpoint, for example "ROLLBAR_API_BASE": "https://rollbar-dev.example.com/api/1".

Codex CLI

Add to your ~/.codex/config.toml:

[mcp_servers.rollbar]
command = "npx"
args = ["-y", "@rollbar/mcp-server@latest"]
env = { "ROLLBAR_ACCESS_TOKEN" = "<project read/write acecss token>" }

Junie

Configure your .junie/mcp/mcp.json as follows:

{
    "mcpServers": {
        "rollbar": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "@rollbar/mcp-server@latest"
            ],
            "env": {
                "ROLLBAR_ACCESS_TOKEN": "<project read/write access token>"
            }
        }
    }
}

VS Code

Configure your .vscode/mcp.json as follows:

{
  "servers": {
    "rollbar": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@rollbar/mcp-server@latest"
      ],
      "env": {
        "ROLLBAR_ACCESS_TOKEN": "<project read/write access token>"
      }
    }
  }
}

Or using a local development installation - see CONTRIBUTING.md.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选