Paylocity MCP Server
Connects Claude Desktop to the Paylocity API to manage employee records, pay statements, and company headcount data through natural language. It includes automated data protection that redacts sensitive information like SSNs and bank account numbers before reaching the model.
README
Paylocity MCP Server
An MCP (Model Context Protocol) server that connects Claude Desktop to the Paylocity API. Sensitive data like SSNs and bank account numbers are automatically redacted before reaching Claude.
Setup
1. Install
git clone <this-repo>
cd payolocity-mcp
npm install
npm run build
2. Get your Paylocity API credentials
You'll need two sets of API keys from your Paylocity admin:
- WebLink API Key (Client ID + Client Secret) — used for employee details, pay statements, and write operations
- NextGen API Key (Client ID + Client Secret) — used for the employee directory search
Both come as password-protected zip files from Paylocity. Ask your Paylocity admin or implementation contact for access.
You'll also need your Company ID — the numeric ID Paylocity assigned to your company (e.g. 348353).
3. Configure Claude Desktop
Open your Claude Desktop config file:
- Mac:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add the paylocity server to mcpServers:
{
"mcpServers": {
"paylocity": {
"command": "node",
"args": ["/full/path/to/payolocity-mcp/dist/server.js"],
"env": {
"PAYLOCITY_CLIENT_ID": "your-weblink-client-id",
"PAYLOCITY_CLIENT_SECRET": "your-weblink-client-secret",
"PAYLOCITY_ENV": "production",
"PAYLOCITY_COMPANY_ID": "your-company-id",
"PAYLOCITY_NEXTGEN_CLIENT_ID": "your-nextgen-client-id",
"PAYLOCITY_NEXTGEN_CLIENT_SECRET": "your-nextgen-client-secret"
}
}
}
}
Replace the placeholder values with your actual credentials and the full path to where you cloned the repo.
4. Restart Claude Desktop
Quit and reopen Claude Desktop. The Paylocity tools will appear automatically.
What you can do
Once connected, you can ask Claude things like:
- "Find Sean Canton in Paylocity"
- "What's Jeremy Allen's job title and department?"
- "Show me the company headcount by department"
- "Pull pay statements for employee 76 for 2025"
- "What are the direct deposit accounts for employee 1?"
Available tools
| Tool | Description |
|---|---|
| search_employees | Find employees by name, title, email, or ID |
| get_employee | Full employee detail (pay, benefits, tax, addresses, contacts) |
| get_pay_statements | Pay history with summary and line-item details |
| get_direct_deposit | Bank account info (numbers redacted) |
| get_company_summary | Headcount and department breakdown |
| update_employee | Change address, title, department, pay rate, status |
| add_earnings | Add a bonus, commission, or other one-time pay |
| add_employee | Create a new employee record |
Data protection
All API responses are scrubbed before reaching Claude:
- SSNs show only the last 4 digits (
***-**-1234) - Bank account numbers are masked
- Routing numbers are fully redacted
- Company FEIN is masked
This happens at the server level — Claude never sees the raw data.
Credentials
- WebLink API secrets expire after 365 days
- NextGen API secrets expire after 365 days
- Check the expiration dates in the zip file names from Paylocity
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。
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。
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。
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。