BioMatrixReport MCP Server

BioMatrixReport MCP Server

Exposes BioMatrixReport APIs as MCP tools for querying employee details, sending WFO attendance report emails, and syncing biometric attendance data via natural language.

Category
访问服务器

README

BioMatrixReport MCP Server

Generated automatically from the BioMatrixReport source repo. Exposes its API as MCP tools so an AI assistant can call them via natural language.

What's in here

  • server.py - the MCP server (mounted at /mcp) plus one tool per API endpoint discovered in the source repo.
  • auth.py / session_store.py - authentication. Credentials and tokens never pass through the assistant - sign-in always happens in a real browser page, and only an opaque session reference reaches the model.
  • config.py - runtime settings, read from environment variables.

1. Configure environment variables

Copy .env.example to .env (locally) or set these in your hosting platform's dashboard:

  • TARGET_APP_BASE_URL - detected as http://localhost:5183 from the source repo. Confirm this is actually where BioMatrixReport is running (dev/staging/prod may differ) and update it if not.

2. Deploy to Render

  1. Push this folder to a new git repo (or use Render's "Deploy from a Blueprint" with the included render.yaml).
  2. In the Render dashboard, create a new Web Service from that repo (Render will detect the Dockerfile), or use the Blueprint if you set one up from render.yaml.
  3. Set the environment variables from step 1 in the Render dashboard.
  4. Deploy. Render will give you a public URL like https://your-service.onrender.com.

3. Connect it to your AI assistant

Add the MCP server URL to your assistant as a remote MCP connector:

https://your-service.onrender.com/mcp

Available tools

  • get_employee_details (GET /get-details) - Fetches an employee's details (name, email, department, manager, active status, etc.) from the external HRIS/Employee API by employee code. Returns the raw JSON employee record.
  • send_weekly_email (POST /sendWeeklyEmail) - Triggers sending of the weekly Work-From-Office (WFO) attendance report email to active employees (and their managers). Validates that attendance data exists for the last Mon/Tue/Wed before sending; if data is missing, sends an alert email instead and returns an error.
  • send_monthly_email (POST /sendMonthlyEmail) - Triggers sending of the monthly WFO attendance report email (with 6-month trend chart and pattern analysis) to active employees for the previous calendar month.
  • send_monthly_report (POST /api/EngineeringHeadReport/sendMonthlyReport) - Generates and emails a company-wide monthly WFO compliance report to the engineering head, including department/band breakdowns, compliance distribution, day-of-week analysis, manager leaderboard, and 6-month trends. Defaults to the previous month if month/year are not supplied.
  • sync_employees_from_hris (POST /api/EmployeeSync/syncFromHRIS) - Syncs employee master data from the external HRIS API into the local database, creating new employee records (default SendEmail='No') or updating existing ones (preserving SendEmail preference). Returns counts of new/updated records and any per-record errors.
  • upload_attendance_csv (POST /api/UserData/upload) - Uploads one or more CSV files containing biometric attendance data (employee ID, datetime, IN/OUT status) and inserts the records into the database.
  • send_monthly_attendance_email (POST /sendMonthlyAttendanceEmail) - Generates an Excel (xlsx) attendance report for all active employees for the previous month and emails it as an attachment to HR.
  • send_weekly_attendance_email (POST /sendWeeklyAttendanceEmail) - Generates a CSV attendance report for the prior complete week and emails it as an attachment to HR.
  • trigger_attendance_sync (POST /api/attendance-sync/trigger) - Manually triggers a sync of biometric attendance transactions (in/out punches) for a given date from the external iClock biometric device API into the AttendanceRecords table. Returns the date synced and the number of records upserted.

Notes from analysis

ASP.NET Core 6 app with no authentication/authorization configured anywhere (no [Authorize] attributes, no auth middleware registered in Program.cs), so all endpoints are unauthenticated. Base URL is only known from the local dev launchSettings.json (http://localhost:5183 / https://localhost:7083) - no deployed/production URL was found in config or docs. The app also calls several external third-party APIs (HRIS at app1.thepsi.com, an internal Employee API at 192.168.3.220:5000, a biometric iClock API, and a SendMail API) but those are outbound dependencies, not endpoints this app exposes, so they were excluded. The GET /get-details endpoint proxies to that internal Employee API.

Local development

pip install -r requirements.txt
cp .env.example .env  # fill in values
python server.py

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
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
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
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
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
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
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
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