Work Integrations MCP
An MCP server that enables interaction with Jira to fetch issues by key and perform JQL searches. It provides a foundation for integrating multiple work systems, with planned support for Slack and GitHub.
README
Work Integrations MCP
This is a small MCP server that exposes tools for multiple work systems (Jira now, with Slack/GitHub and others planned).
Current tools
jira_get_issue- Fetch a Jira issue by keyjira_search- Search Jira using JQLslack_get_message_by_url- Fetch a Slack message by URLslack_get_channel_history- Fetch recent Slack messagesslack_find_channel- Resolve channel name to IDslack_find_user- Resolve user by email or display name
Setup
-
Install dependencies:
npm install
-
Configure environment variables (examples):
JIRA_BASE=https://company.atlassian.netJIRA_EMAIL=you@company.comJIRA_TOKEN=your_api_tokenJIRA_API_VERSION=3SLACK_TOKEN=xoxb-your-slack-bot-token
-
Register the MCP server in Cursor (
~/.cursor/mcp.json):{ "mcpServers": { "work-integrations-mcp": { "command": "npx", "args": [ "tsx", "/ABS/PATH/jira-mcp/server.ts" ], "env": { "JIRA_BASE": "https://company.atlassian.net", "JIRA_EMAIL": "you@company.com", "JIRA_TOKEN": "your_api_token", "JIRA_API_VERSION": "3", "SLACK_TOKEN": "xoxb-your-slack-bot-token" } } } } -
Restart Cursor.
Usage examples
- "Use
jira_get_issuewith keyCVR-248" - "Search Jira with JQL:
project = CVR ORDER BY updated DESC" - "Use
slack_get_message_by_urlwith urlhttps://..." - "Use
slack_get_channel_historywith channelgeneral" - "Use
slack_find_userwith emailuser@company.com"
Slack setup notes
Create a Slack App and install it in your workspace. Minimum scopes for public channels:
channels:readchannels:historyusers:readusers:read.email
For private channels, add:
groups:readgroups:history
Extending
Add new tools for Slack, GitHub, or other services by adding a new folder
under services/ and registering the module in server.ts:
- Create
services/<service>/client.tsfor auth + API calls - Create
services/<service>/tools.tsexporting aToolModule - Import the module in
server.tsand pass it tomergeToolModules - Add any new env variables in the Cursor MCP config if needed
Keep the tool names stable so existing prompts continue to work.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。