Work Integrations MCP
工作集成 MCP
这是一个小型 MCP 服务器,为多个工作系统提供工具(目前支持 Jira,计划支持 Slack/GitHub 等)。
当前工具
jira_get_issue- 通过键获取 Jira 问题jira_search- 使用 JQL 搜索 Jiraslack_get_message_by_url- 通过 URL 获取 Slack 消息slack_get_channel_history- 获取最近的 Slack 消息slack_find_channel- 将频道名称解析为 IDslack_find_user- 通过电子邮件或显示名称解析用户confluence_get_page- 通过 ID 获取 Confluence 页面(包含页脚 + 带有嵌套回复的内联评论)confluence_get_page_by_url- 通过 URL 获取 Confluence 页面(包含页脚 + 带有嵌套回复的内联评论)confluence_search- 使用 CQL 搜索 Confluence
Related MCP server: Personal JIRA MCP
设置
安装依赖:
npm install
配置环境变量(示例):
JIRA_BASE=https://company.atlassian.netJIRA_EMAIL=you@company.comJIRA_TOKEN=your_api_tokenJIRA_API_VERSION=3SLACK_TOKEN=xoxb-your-slack-bot-tokenCONFLUENCE_BASE=https://company.atlassian.net/wikiCONFLUENCE_EMAIL=you@company.comCONFLUENCE_TOKEN=your_api_token
在 Cursor 中注册 MCP 服务器 (
~/.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", "CONFLUENCE_BASE": "https://company.atlassian.net/wiki", "CONFLUENCE_EMAIL": "you@company.com", "CONFLUENCE_TOKEN": "your_api_token" } } } }重启 Cursor。
使用示例
“使用
jira_get_issue,键为CVR-248”“使用 JQL 搜索 Jira:
project = CVR ORDER BY updated DESC”“使用
slack_get_message_by_url,URL 为https://...”“使用
slack_get_channel_history,频道为general”“使用
slack_find_user,电子邮件为user@company.com”“使用
confluence_get_page,ID 为123456”“使用
confluence_get_page_by_url,URL 为https://.../wiki/...”“使用
confluence_search,CQL 为space = DOCS and type = page”
Slack 设置说明
创建一个 Slack 应用并将其安装到您的工作区中。公共频道的最低权限范围:
channels:readchannels:historyusers:readusers:read.email
对于私有频道,请添加:
groups:readgroups:history
扩展
通过在 services/ 下添加新文件夹并在 server.ts 中注册模块,可以为 Slack、GitHub 或其他服务添加新工具:
创建
services/<service>/client.ts用于身份验证和 API 调用创建
services/<service>/tools.ts并导出ToolModule在
server.ts中导入该模块并将其传递给mergeToolModules如果需要,在 Cursor MCP 配置中添加任何新的环境变量
请保持工具名称稳定,以便现有的提示词能够继续正常工作。
This server cannot be deployed
Maintenance
Related MCP Connectors
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
A MCP server built for developers enabling Git based project management with project and personal…
Personal assistant MCP server with search, execute, packages, jobs, secrets, and integrations.
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
Related MCP Servers
- AlicenseCqualityDmaintenanceAn MCP server that enables communication with Jira, allowing users to perform operations like getting, searching, creating, and editing issues through natural language interaction.176 npmMIT
- AlicenseCqualityCmaintenanceAn MCP server that enables AI assistants to interact with JIRA, allowing for querying issue details, creating and updating work items, and managing attachments through a standardized interface.124MIT
- AlicenseNot gradedqualityAmaintenanceMCP server for interacting with Jira Cloud instances. Enables issue management, JQL queries, project and sprint management, and batch operations via natural language interfaces.206 npm4MIT
- AlicenseNot gradedqualityDmaintenanceA comprehensive, production-ready MCP server for seamless Jira Cloud integration, enabling AI agents and custom applications to manage boards, issues, users, projects, and workflows via natural language commands.383 npm4MIT