manoj-mcp

manoj-mcp

A personal MCP server that enables Claude to interact with Jira, Confluence, Gmail, Google Drive, and Slack via natural language from any device.

Category
访问服务器

README

Manoj's Personal MCP Server

Remote MCP server giving Claude access to Jira, Confluence, Gmail, Drive, and Slack — from any device including phone.

Tools included

Tool What it does
jira_create_ticket Create a Jira issue with summary, description, priority, labels
jira_search Search issues by plain English or JQL
jira_get_issue Get full details of any issue
jira_transition Move issue to new status (In Progress, Done, etc.)
jira_add_comment Add a comment to any issue
jira_my_issues Get all your open issues
confluence_search Search pages by keyword
confluence_get_page Read full page content
confluence_create_page Create a new page in any space
gmail_search Search email threads
gmail_read_thread Read a full email thread
gmail_create_draft Create a draft (does not send)
gmail_unread_count Get unread inbox count
drive_search Search Drive files by name or content
drive_read_doc Read a Google Doc's content
drive_list_folder List files in a folder
slack_search Search messages across all channels
slack_read_channel Read recent messages in a channel
slack_find_channel Find a channel ID by name
slack_send_message Send a message to a channel

Deploy to Railway (free, ~15 minutes)

Step 1 — Push to GitHub

cd manoj-mcp
git init
git add .
git commit -m "initial commit"

Then create a new repo on github.com (name it manoj-mcp, private) and:

git remote add origin https://github.com/YOUR_USERNAME/manoj-mcp.git
git push -u origin main

Step 2 — Deploy on Railway

  1. Go to railway.app → Sign in with GitHub
  2. Click New ProjectDeploy from GitHub repo → select manoj-mcp
  3. Railway auto-detects Node.js and deploys. Wait ~2 minutes.
  4. Go to Settings → Networking → click Generate Domain → copy your URL e.g. https://manoj-mcp-production.up.railway.app

Step 3 — Set environment variables in Railway

Go to your service → Variables tab → add all from .env.example:

Variable Where to get it
MCP_AUTH_TOKEN Make up a long random string — use a password generator
JIRA_DOMAIN prathamdigitalteam.atlassian.net
JIRA_EMAIL manoj.mahale@pratham.org
JIRA_API_TOKEN id.atlassian.com/manage-profile/security/api-tokens
GMAIL_ACCESS_TOKEN See below
SLACK_BOT_TOKEN See below

Getting GMAIL_ACCESS_TOKEN:

  1. Go to developers.google.com/oauthplayground
  2. Select scopes: Gmail API v1 (gmail.readonly, gmail.compose) + Drive API v3 (drive.readonly) + Google Docs API v1 (documents.readonly)
  3. Click Authorize → Exchange for tokens → copy Access Token
  4. Note: access tokens expire in 1 hour. For permanent access you'll need OAuth refresh flow — we'll set that up next.

Getting SLACK_BOT_TOKEN:

  1. Go to api.slack.com/apps → Create New App → From Scratch
  2. Name: Manoj MCP → pick your workspace
  3. Go to OAuth & Permissions → Bot Token Scopes → add: channels:read, channels:history, search:read, chat:write
  4. Click Install to Workspace → copy Bot User OAuth Token (starts with xoxb-)

Step 4 — Test

curl https://your-railway-url.railway.app/health
# Should return: {"status":"ok","service":"manoj-mcp"}

curl -H "Authorization: Bearer YOUR_TOKEN" https://your-railway-url.railway.app/sse
# Should open SSE stream

Step 5 — Connect in Claude.ai on phone

  1. Open Claude.ai on phone → Settings → MCP Servers (or Integrations)
  2. Add new server:
    • URL: https://your-railway-url.railway.app/sse
    • Auth: Bearer YOUR_MCP_AUTH_TOKEN
  3. Save → you'll see all 20 tools available

Local development

npm install
cp .env.example .env
# Fill in .env values
npm run dev

Server runs on http://localhost:3000

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
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
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
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
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
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
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
mcp-server-qdrant

mcp-server-qdrant

这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。

官方
精选
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选