attendance-mcp
Exposes BIPO attendance tools (clock punch, leave/OT requests, approvals, reports) to the BIPO AI assistant via a stateless proxy that authenticates callers and forwards HRMS tokens.
README
attendance-mcp
MCP server that exposes BIPO attendance tools to the BIPO AI assistant.
It is a thin, stateless proxy: each tool authenticates the caller (BIPO), then forwards the logged-in user's HRMS token to the existing BIPO HRMS / attendance API, which enforces all role permissions (Employee, Coordinator, Manager, HR).
- Language / framework: Python + FastMCP
- Transport: remote streamable-HTTP
- Auth:
- Inbound (BIPO → server):
x-service-keyvalidated againstMCP_SERVICE_KEY; the user's HRMS token arrives inX-HRMS-Authorization. - Outbound (server → HRMS API): the user's HRMS token forwarded as
X-HRMS-Authorization.
- Inbound (BIPO → server):
Status: skeleton (pending HRMS API)
All 13 tools are wired and callable, but the real HRMS endpoints are not yet
known. Every tool currently returns a structured PENDING_HRMS_API placeholder.
Only src/attendance_mcp/bipo_client.py needs to change once the HRMS team
provides the endpoints — replace each self._pending(...) with self._request(...).
See bipo-attendance-mcp-tools.html for the tool list shared with the HRMS team.
Tools
| Role | Tools | Scenarios |
|---|---|---|
| Employee | clock_punch, submit_clock_amendment, submit_leave_request, submit_ot_request, get_ot_request, cancel_ot_request |
1–5 |
| Shared | get_attendance_status |
6 |
| Coordinator | submit_batch_ot_request |
7 |
| Manager | list_pending_approvals, approve_request, reject_request |
8 |
| HR | get_daily_exceptions, send_clock_reminders, generate_attendance_report |
9–11 |
Scenario 5 guardrail: OT requests cannot be deleted — only cancelled. There is intentionally no
delete_ot_requesttool.
Setup
python -m venv .venv
.venv\Scripts\activate # Windows
pip install -e ".[dev]"
cp .env.example .env # then edit BIPO_API_BASE_URL etc.
Run
attendance-mcp # streamable-HTTP on MCP_HOST:MCP_PORT (default 127.0.0.1:8000)
Test
pytest
Layout
src/attendance_mcp/
server.py FastMCP app + transport
config.py env settings
auth.py reads the caller's bearer token
bipo_client.py HRMS API client (placeholder calls; the only file to edit later)
tools/ one module per role, each exposing register(mcp)
tests/ in-memory tests (no live API needed)
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.