sipap-data-mcp
Provides read-only access to sports data, odds intelligence, and historical stats via 10 MCP tools, with fast response times through Redis caching.
README
SIPAP Data MCP Server
Consolidated data access MCP (Model Context Protocol) server providing read-only access to sports data stored in Aurora PostgreSQL.
Overview
sipap-data-mcp consolidates 3 separate MCPs into a single unified server:
- Sports data (matches, teams, leagues)
- Odds intelligence (betting odds from 37+ bookmakers)
- Historical data (season stats, head-to-head)
Features
-
10 Tools for AI agents:
- 4 match tools (schedule, details, live, search)
- 3 team tools (stats, standings, head-to-head)
- 2 odds tools (current odds, movement tracking)
- 1 historical tool (season aggregations)
-
Fast Response Times: <100ms via Redis caching
-
JSON-RPC 2.0 Protocol: Standard MCP protocol
-
Lambda ARM64 Deployment: Cost-effective, auto-scaling
-
Read-Only Access: No writes (batch scraper handles writes)
Installation
# Clone repository
cd /Users/charlesotuya/AI-Odi/sentinel/sipap/repos/sipap-data-mcp
# Create virtual environment
python3.12 -m venv .venv
source .venv/bin/activate
# Install dependencies
pip install -e '.[dev]'
Development
Running Tests
# Run all tests
pytest
# Run with coverage
pytest --cov=src/sipap_data_mcp --cov-report=term-missing
# Run specific test file
pytest tests/unit/database/test_aurora.py -v
Type Checking
mypy src/sipap_data_mcp --strict
Linting
ruff check src/ tests/
ruff check --fix src/ tests/ # Auto-fix issues
Quality Gates
Before deploying, all quality gates must pass:
- Tests: 80%+ coverage, all tests passing
- Type Checking: Zero mypy errors (strict mode)
- Linting: Zero ruff errors
- Imports: All public APIs importable
# Run all quality gates
pytest --cov=src/sipap_data_mcp --cov-fail-under=80 && \
mypy src/sipap_data_mcp --strict && \
ruff check src/ tests/
Project Structure
sipap-data-mcp/
├── src/sipap_data_mcp/
│ ├── tools/ # MCP tool implementations
│ ├── database/ # Aurora PostgreSQL client
│ ├── models/ # TypedDict data models
│ └── exceptions/ # Exception hierarchy
├── tests/
│ ├── unit/ # Unit tests
│ ├── integration/ # Integration tests
│ └── fixtures/ # Test data fixtures
└── examples/ # Working examples
License
Proprietary - SIPAP Project
Status
🚧 Under Development - Phase 2.B: Data Layer (Week 5)
Current: Day 1 - Repository setup and database client (TDD)
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.