allpets_mcp
MCP server for AllPets Clinic analytics, providing weekly KPI dashboards, natural language SQL queries, and Excel report generation.
README
allpets_mcp
Fully self-contained MCP server for AllPets Clinic & Beyond analytics. All business logic lives inside this repo — no dependency on any sibling folder at runtime.
Setup (one-time)
cd C:\Users\sathv\Desktop\allpets_mcp
# Create venv
python -m venv venv
# Install dependencies
.\venv\Scripts\pip.exe install -r requirements.txt
# Fill in credentials (already populated for local dev)
notepad .env
Local test
# Dev inspector — opens browser UI to call tools manually
.\venv\Scripts\python.exe -m mcp dev server.py
# Or run directly (exits immediately in stdio mode — expected)
.\venv\Scripts\python.exe server.py
Claude Desktop setup
- Open
%APPDATA%\Claude\claude_desktop_config.json - Add the
allpetsentry inside"mcpServers":
{
"mcpServers": {
"allpets": {
"command": "C:\\Users\\sathv\\Desktop\\allpets_mcp\\venv\\Scripts\\python.exe",
"args": ["C:\\Users\\sathv\\Desktop\\allpets_mcp\\server.py"]
}
}
}
- Restart Claude Desktop completely (quit and reopen).
- The tool icon appears in the chat input — click it to see the 4 AllPets tools.
Phase 1 tools
| Tool | What it does |
|---|---|
get_current_week_dates |
Returns this ISO week's Monday/Sunday |
get_weekly_dashboard |
Full KPI dashboard for a date range |
ask_analytics |
Freeform NL2SQL question |
generate_excel_report |
Weekly dashboard as .xlsx (base64) |
Project structure
allpets_mcp/
├── server.py ← Entry point (stdio MCP server)
├── config.py ← DB engine + env loading (self-contained)
├── dashboard_queries.py ← Pre-computed weekly KPI engine
├── nl2sql_agent.py ← 5-step LangGraph NL2SQL pipeline
├── sql_dynamic_agent.py ← SQL generation + retry (~1970 lines)
├── excel_export.py ← openpyxl report generator
├── etc/secrets/
│ └── schema_all.txt ← Full DB schema DDL (used by SQL agent)
├── adapters/
│ ├── dashboard.py ← Wraps DashboardService.run_weekly()
│ ├── analytics.py ← Wraps nl2sql_agent.run_agent()
│ └── excel.py ← Wraps generate_excel() → base64
├── tools/
│ ├── dashboard.py ← get_weekly_dashboard, get_current_week_dates
│ ├── analytics.py ← ask_analytics
│ └── reports.py ← generate_excel_report
├── .env ← All credentials (DB + OpenAI)
└── requirements.txt
Updating business logic
When dashboard_queries.py, nl2sql_agent.py, sql_dynamic_agent.py, or excel_export.py
change in allpets_new_schema, copy the updated file here:
Copy-Item ..\allpets_new_schema\dashboard_queries.py .\dashboard_queries.py -Force
Copy-Item ..\allpets_new_schema\nl2sql_agent.py .\nl2sql_agent.py -Force
Copy-Item ..\allpets_new_schema\sql_dynamic_agent.py .\sql_dynamic_agent.py -Force
Copy-Item ..\allpets_new_schema\excel_export.py .\excel_export.py -Force
Copy-Item ..\allpets_new_schema\etc\secrets\schema_all.txt .\etc\secrets\schema_all.txt -Force
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.