SuccessFactors MCP Server
An MCP server for interacting with SAP SuccessFactors OData API to retrieve and update employee/user data.
README
SuccessFactors MCP Server
An MCP (Model Context Protocol) server for interacting with SAP SuccessFactors OData API to retrieve and update employee/user data.
Features
- get_user_data: Retrieve employee data with all specified fields
- post_user_data: Update employee/user information
- get_user_statistics: Get aggregate statistics about all users
- search_user_by_email: Find users by email and return userId/firstName/lastName/email
- manage_user_fields: Get or update all 47 standard user fields (comprehensive field management)
- get_complete_employee_data: Retrieve complete employee data with all navigation properties (full OData entry)
- get_manager_hr: Retrieve manager and/or HR information
- update_user_odata: Update user data using the upsert endpoint with exact OData format (camelCase fields). WARNING: This operation will modify employee data in the SAP SuccessFactors system. Changes cannot be automatically undone.
- update_manager_hr: Update manager and/or HR assignments. WARNING: This operation will modify employee data in the SAP SuccessFactors system. Changes cannot be automatically undone.
Setup
- Install dependencies:
npm install
- Build the project:
npm run build
- Run the server:
npm start
For development with auto-reload:
npm run dev
Configuration
All sensitive configuration (API URL, username, and password) is stored in a .env file.
- Copy the example file:
copy .env.example .env
- Edit the
.envfile with your credentials:
SF_API_URL=https://apisalesdemo2.successfactors.eu/odata/v2
SF_USERNAME=your-username-here
SF_PASSWORD=your-password-here
Important: The .env file is already in .gitignore and will not be committed to version control. Always keep your credentials secure!
MCP Client Configuration
To use this server with an MCP client (like Claude Desktop), add it to your MCP configuration file:
{
"mcpServers": {
"successfactors": {
"command": "node",
"args": ["C:\\Users\\Desktop\\SF-MCP-01\\dist\\index.js"]
}
}
}
Available Tools
get_user_data
search_user_by_email
Search users by email and return basic identity info.
Parameters:
email(required): Email address to search (exact match)
Returns: Array of matches with userId, firstName, lastName, and email.
Example request (OData): GET /odata/v2/User?$filter=email eq 'user.email@example.com'
Retrieves employee/user data from SuccessFactors.
Parameters:
userId(required): User ID (USERID), Employee ID (EMPID), or Email addressfields(optional): Array of specific fields to retrieve. If not provided, returns all standard fields.
Returns: JSON object with user data including:
- STATUS, USERID, USERNAME, FIRSTNAME, LASTNAME, MI, GENDER, EMAIL
- MANAGER, HR, DEPARTMENT, JOBCODE, DIVISION, LOCATION, TIMEZONE
- HIREDATE, EMPID, TITLE, BIZ_PHONE, FAX
- ADDR1, ADDR2, CITY, STATE, ZIP, COUNTRY
- REVIEW_FREQ, LAST_REVIEW_DATE
- CUSTOM01 through CUSTOM15
- MATRIX_MANAGER, DEFAULT_LOCALE, PROXY
- CUSTOM_MANAGER, SECOND_MANAGER, LOGIN_METHOD
- PERSON_GUID, PERSON_ID_EXTERNAL
post_user_data
Updates employee/user data in SuccessFactors.
Parameters:
userId(required): User ID to updatedata(required): Object containing key-value pairs of fields to update
Returns: Confirmation of successful update with updated fields list.
Implementation detail: This operation uses the SuccessFactors upsert endpoint: POST /upsert?purgeType=record.
get_user_statistics
Retrieves aggregate statistics about all users.
Parameters:
filters(optional): Object with filters for statistics
Returns: Statistics including:
- Total users count
- Active/inactive users
- Breakdown by gender, department, location, and status
get_manager_hr
Retrieves manager and/or HR information for a specific user.
Parameters:
userId(required): User ID (USERID), Employee ID (EMPID), or Email address to querygetManager(optional): Whether to retrieve manager information (default: true)getHR(optional): Whether to retrieve HR information (default: true)
Returns: JSON object with:
- User ID information
- Manager details (userId, username, firstName, lastName, email) if requested
- HR details (userId, username, firstName, lastName, email) if requested
- null values if manager/HR is not assigned
update_manager_hr
Updates manager and/or HR assignment for a user.
Parameters:
userId(required): User ID to updatemanagerId(optional): New manager User ID to assign (can be USERID, EMPID, or EMAIL)hrId(optional): New HR User ID to assign (can be USERID, EMPID, or EMAIL)
Note: At least one of managerId or hrId must be provided.
Returns: Confirmation of successful update with assigned manager/HR IDs.
manage_user_fields
Get or update all standard user fields in SuccessFactors. This is a comprehensive tool that supports all 47 standard fields.
Parameters:
action(required): Either"get"to retrieve fields or"update"to modify fieldsuserId(required): User ID (USERID), Employee ID (EMPID), or Email addressfields(optional):- For
"get"action: Object specifying which fields to retrieve (keys are field names). If not provided, returns all fields. - For
"update"action: Required - Object containing field names and values to update (e.g.,{"FIRSTNAME": "John", "LASTNAME": "Doe"})
- For
Supported Fields (all 47 fields): STATUS, USERID, USERNAME, FIRSTNAME, LASTNAME, MI, GENDER, EMAIL, MANAGER, HR, DEPARTMENT, JOBCODE, DIVISION, LOCATION, TIMEZONE, HIREDATE, EMPID, TITLE, BIZ_PHONE, FAX, ADDR1, ADDR2, CITY, STATE, ZIP, COUNTRY, REVIEW_FREQ, LAST_REVIEW_DATE, CUSTOM01 through CUSTOM15, MATRIX_MANAGER, DEFAULT_LOCALE, PROXY, CUSTOM_MANAGER, SECOND_MANAGER, LOGIN_METHOD, PERSON_GUID, PERSON_ID_EXTERNAL
Returns:
- For
"get": All requested fields with their current values (null if not set), plus list of all available fields - For
"update": Confirmation with list of updated fields and their new values
Implementation detail: The update action uses the SuccessFactors upsert endpoint: POST /upsert?purgeType=record.
get_complete_employee_data
Retrieve complete employee data with all fields and navigation properties. This returns the full OData entry as returned by SuccessFactors API, similar to fetching User('empId') directly. Useful for getting comprehensive employee information including all available navigation links and expanded properties.
Parameters:
userId(required): User ID (USERID), Employee ID (EMPID), or Email addressexpandProperties(optional): Array of navigation properties to expand (e.g.,["personKeyNav", "manager", "hr", "empInfo"]). If not provided, defaults to common properties: personKeyNav, manager, hr, empInfo, secondManager, matrixManager, customManager.format(optional): Response format -"json"(default) or"xml". XML format returns the raw OData XML entry.
Returns:
- Complete employee data structure with all fields and navigation properties
- For JSON format: Structured object with completeData field containing all employee information
- For XML format: Raw OData XML entry (similar to the example provided)
update_user_odata
Update user data using the SuccessFactors upsert endpoint with exact OData format matching SuccessFactors API. Accepts fields in camelCase format (firstName, lastName, email, status, timeZone, etc.) and automatically formats manager and HR with proper __metadata structure.
Parameters:
userId(required): User ID to update (internal user ID)username(optional): Username (defaults to userId if not provided)status(optional): User status (e.g., "t" for active)firstName(optional): First namelastName(optional): Last namegender(optional): Gender (M/F)email(optional): Email addressdepartment(optional): DepartmenttimeZone(optional): Time zone (e.g., "US/Eastern", "Asia/Jerusalem")managerId(optional): Manager User ID, or "NO_MANAGER" to remove managerhrId(optional): HR User ID, or "NO_HR" to remove HRadditionalFields(optional): Object with additional fields in camelCase format
Returns: Confirmation with the complete payload that was sent and the API response.
Implementation detail: This tool performs POST /upsert?purgeType=record with a SFOData.User payload.
Notes
- WARNING - DEMONSTRATION PURPOSES ONLY
- This code is NOT PRODUCTION-READY and has been created solely for DEMONSTRATION AND TESTING PURPOSES.
- Do not use this in a live production environment.
- Before deploying to production, ensure proper development, testing, security review, and compliance with all relevant standards and regulations.
- WARNING: This operation will modify employee data in the SAP SuccessFactors system. Changes cannot be automatically undone.
- The server uses Basic Authentication with the provided credentials
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。