feat: SSE/HTTP transport for enterprise HTTPS deployment (v0.7.1)

- Add --transport sse|streamable-http CLI args (env: MCP_TRANSPORT/HOST/PORT)
- Rebuild Dockerfile for SSE default with uvicorn
- Add docker-compose.yml with Caddy reverse proxy for auto-TLS
- Add Caddyfile template for Let's Encrypt HTTPS
- Add docs/DEPLOYMENT.md: comprehensive enterprise deployment guide
- Add 'sse' optional dependency group (uvicorn) in pyproject.toml
- Update README: enterprise-ready features, Copilot Studio, deployment docs
- Enables Microsoft Copilot Studio integration via HTTPS MCP endpoint

Author: LGDiMaggio

.claude/settings.local.json

@@ -0,0 +1,15 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(powershell -Command \"cd ''c:\\\\Users\\\\d044653\\\\OneDrive - Politecnico di Torino\\\\predictive-maintenance-mcp''; .\\\\.venv\\\\Scripts\\\\python.exe -c \"\"import pathlib; before = set\\(pathlib.Path\\(''.''\\).glob\\(''*/''\\)\\); import predictive_maintenance_mcp; after = set\\(pathlib.Path\\(''.''\\).glob\\(''*/''\\)\\); new_dirs = after - before; print\\(''FAIL: dirs create: '' + str\\(new_dirs\\)\\) if new_dirs else print\\(''OK: nessuna directory creata a import-time''\\); from predictive_maintenance_mcp import mcp, main, __version__; print\\(''OK: mcp='' + type\\(mcp\\).__name__ + '' version='' + __version__\\)\"\"\")",
+      "Bash(powershell -Command \"cd ''c:\\\\Users\\\\d044653\\\\OneDrive - Politecnico di Torino\\\\predictive-maintenance-mcp''; .\\\\.venv\\\\Scripts\\\\python.exe -m pytest tests/ -x -q --no-header --tb=short 2>&1 | Select-Object -First 60\")",
+      "Bash(powershell -Command \"cd ''c:\\\\Users\\\\d044653\\\\OneDrive - Politecnico di Torino\\\\predictive-maintenance-mcp''; .\\\\.venv\\\\Scripts\\\\python.exe -c \"\"import predictive_maintenance_mcp; print\\(predictive_maintenance_mcp.__file__\\)\"\"\")",
+      "Bash(powershell -Command \"cd ''c:\\\\Users\\\\d044653\\\\OneDrive - Politecnico di Torino\\\\predictive-maintenance-mcp''; .\\\\.venv\\\\Scripts\\\\python.exe -m pytest tests/ -x -q --no-header --tb=short 2>&1 | Select-Object -First 80\")",
+      "Bash(powershell -Command \"cd ''c:\\\\Users\\\\d044653\\\\OneDrive - Politecnico di Torino\\\\predictive-maintenance-mcp''; git status\")",
+      "Bash(powershell -Command \"cd ''c:\\\\Users\\\\d044653\\\\OneDrive - Politecnico di Torino\\\\predictive-maintenance-mcp''; git log --oneline -5\")",
+      "Bash(powershell -Command \"cd ''c:\\\\Users\\\\d044653\\\\OneDrive - Politecnico di Torino\\\\predictive-maintenance-mcp''; git add pyproject.toml src/config.py src/signal_loader.py src/document_reader.py src/machinery_diagnostics_server.py src/report_generator.py tests/test_obsolete_tools_removed.py tests/test_real_data.py tests/test_reports.py tests/test_unit_conversion.py\")",
+      "Bash(powershell -Command \"cd ''c:\\\\Users\\\\d044653\\\\OneDrive - Politecnico di Torino\\\\predictive-maintenance-mcp''; git commit -m ''refactor: eliminate import-time side effects and centralize path config:*)",
+      "Bash(powershell -Command \"cd ''c:\\\\Users\\\\d044653\\\\OneDrive - Politecnico di Torino\\\\predictive-maintenance-mcp''; git push origin main\")"
+    ]
+  }
+}

CHANGELOG.md

@@ -5,6 +5,18 @@ All notable changes to the Predictive Maintenance MCP Server project will be doc
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.7.1] - 2025-07-15
+
+### Added
+- **SSE & Streamable-HTTP transport** — `main()` now accepts `--transport sse|streamable-http` (or env var `MCP_TRANSPORT`) via argparse CLI, enabling remote HTTPS deployment for Microsoft Copilot Studio and other networked MCP clients. `--host` / `--port` (or `MCP_HOST` / `MCP_PORT`) configure the listen address.
+- **Docker Compose + Caddy** — New `docker-compose.yml` with `mcp-server` service (SSE by default) and commented-out Caddy reverse proxy for automatic Let's Encrypt HTTPS certificates. New `Caddyfile` template.
+- **HTTPS Deployment guide** — New `docs/DEPLOYMENT.md` covering local SSE testing, Docker Compose + Caddy auto-TLS, nginx reverse proxy, Azure/cloud deployment, Copilot Studio connection, and CLI reference.
+
+### Changed
+- **Dockerfile** rebuilt for SSE default — installs `uvicorn`, sets `MCP_TRANSPORT=sse`, `MCP_HOST=0.0.0.0`, `EXPOSE 8000`
+- README updated: enterprise-ready features, Copilot Studio mention, deployment docs table, roadmap progress
+- Version bumped to 0.7.1
+
 ## [0.7.0] - 2025-07-14
 
 ### Added

CITATION.cff

@@ -1,8 +1,8 @@
 cff-version: 1.2.0
 message: "If you use this software, please cite it as below."
 title: "Predictive Maintenance MCP Server: An open-source framework for integrating Large Language Models with predictive maintenance and fault diagnosis workflows"
-version: 0.7.0
-date-released: 2025-07-14
+version: 0.7.1
+date-released: 2025-07-15
 authors:
   - family-names: Di Maggio
     given-names: Luigi Gianpio
@@ -52,7 +52,7 @@ preferred-citation:
     - family-names: Di Maggio
       given-names: Luigi Gianpio
   year: 2026
-  version: 0.7.0
+  version: 0.7.1
   repository-code: "https://github.com/LGDiMaggio/predictive-maintenance-mcp"
   license: MIT
   doi: "10.5281/zenodo.17611542"

Caddyfile

@@ -0,0 +1,6 @@
+# Replace mcp.example.com with your actual domain.
+# Caddy auto-provisions TLS certificates via Let's Encrypt.
+
+mcp.example.com {
+    reverse_proxy mcp-server:8000
+}

Dockerfile

@@ -10,8 +10,8 @@ RUN pip install --no-cache-dir --upgrade pip setuptools wheel
 COPY pyproject.toml ./
 COPY src/ ./src/
 
-# Install the package
-RUN pip install --no-cache-dir .
+# Install the package (with uvicorn for SSE/HTTP transport)
+RUN pip install --no-cache-dir ".[full]" uvicorn
 
 # --- Production stage ---
 FROM python:3.11-slim
@@ -36,8 +36,14 @@ RUN mkdir -p /app/reports /app/models /app/resources/cache
 ENV PYTHONUNBUFFERED=1
 ENV PYTHONDONTWRITEBYTECODE=1
 
+# Default: SSE transport on 0.0.0.0:8000 (override via env or CLI)
+ENV MCP_TRANSPORT=sse
+ENV MCP_HOST=0.0.0.0
+ENV MCP_PORT=8000
+
+EXPOSE 8000
+
 # Health check (verify imports work)
 RUN python -c "from src.machinery_diagnostics_server import mcp; print('Server imports OK')"
 
-# Default command: run the MCP server via stdio
-ENTRYPOINT ["python", "src/machinery_diagnostics_server.py"]
+ENTRYPOINT ["predictive-maintenance-mcp"]

README.md

@@ -81,7 +81,8 @@ This project is built around the **Model Context Protocol (MCP)** — an open st
 
 - **🔌 Plug-and-play** — Add new analysis tools (thermography, oil analysis, acoustics) as simple Python functions — the LLM discovers them automatically
 - **🔒 Local processing** — Raw signals never leave your machine; only computed results (peaks, RMS, diagnoses) flow to the LLM. Use a [local LLM](https://ollama.com/) for full air-gapped privacy
-- **🤖 LLM-agnostic** — Works with Claude, ChatGPT, or any MCP-compatible client
+- **🤖 LLM-agnostic** — Works with Claude, ChatGPT, **Microsoft Copilot Studio**, or any MCP-compatible client
+- **🌐 Enterprise-ready** — Deploy as HTTPS server (SSE transport) for corporate environments with Docker + auto-TLS
 - **🧱 Modular** — Use only the tools you need, extend with your own
 
 ---
@@ -249,14 +250,19 @@ pip install -e .
 ### Run the Server
 
 ```bash
-# Via module (works with both pip install and editable install)
+# Default: stdio transport (Claude Desktop, VS Code)
 python -m predictive_maintenance_mcp
-
-# Via console script (after pip install)
 predictive-maintenance-mcp
+
+# SSE transport for remote/enterprise clients (Copilot Studio, networked)
+predictive-maintenance-mcp --transport sse --host 0.0.0.0 --port 8080
+
+# Docker (SSE mode by default)
+docker compose up -d
 ```
 
 📖 **Detailed Installation Guide**: See [INSTALL.md](INSTALL.md) for troubleshooting and advanced setup.
+📖 **HTTPS Deployment**: See [DEPLOYMENT.md](docs/DEPLOYMENT.md) for enterprise deployment with TLS.
 
 ---
 
@@ -636,6 +642,7 @@ Generate FFT report for baseline_1.csv
 |----------|----------|-------------|
 | [**Quickstart for Engineers**](docs/QUICKSTART_ENGINEER.md) | 🔧 Engineers | Get results fast, no coding required |
 | [**Quickstart for Developers**](docs/QUICKSTART_DEVELOPER.md) | 💻 Developers | Understand MCP, extend the server |
+| [**HTTPS Deployment**](docs/DEPLOYMENT.md) | 🏢 Enterprise | Docker + HTTPS for Copilot Studio and remote clients |
 | [EXAMPLES.md](EXAMPLES.md) | Everyone | Complete diagnostic workflows with step-by-step tutorials |
 | [INSTALL.md](INSTALL.md) | Everyone | Detailed installation and troubleshooting guide |
 | [CONTRIBUTING.md](CONTRIBUTING.md) | Contributors | How to contribute (for every skill level) |
@@ -715,8 +722,10 @@ npx @modelcontextprotocol/inspector python -m predictive_maintenance_mcp
 
 ## 🚀 Roadmap
 
-### ✨ Recent: v0.7.0 — Vector Search, OCR & DOCX Reports
+### ✨ Recent: v0.7.0–0.7.1 — Vector Search, OCR, DOCX & HTTPS Transport
 
+- 🌐 **SSE / Streamable-HTTP transport** — Deploy as HTTPS server for Microsoft Copilot Studio and remote MCP clients
+- 🐳 **Docker Compose + Caddy** — One-command deployment with automatic TLS certificates
 - 🔎 **FAISS vector search** — Semantic document retrieval with sentence-transformers (TF-IDF fallback when not installed)
 - 🔍 **OCR for scanned PDFs** — Automatic Tesseract OCR fallback for image-based equipment manuals
 - 📝 **DOCX diagnostic reports** — Structured Word documents with statistics, peaks, ISO evaluation, and diagnostic summary
@@ -730,7 +739,8 @@ Each item below links to an open issue where you can **discuss, contribute, or c
 |----------|-------------|--------|--------------|
 | ✅ Done | **Parquet/MAT/WAV/NPY data format support** | v0.5.0 | — |
 | 🔴 High | **Customizable ISO report thresholds** | Open | [Good First Issue](https://github.com/LGDiMaggio/predictive-maintenance-mcp/issues) |
-| 🔴 High | **Docker image for zero-install setup** | Open | [Help Wanted](https://github.com/LGDiMaggio/predictive-maintenance-mcp/issues) |
+| ✅ Done | **HTTPS / SSE transport for Copilot Studio** | v0.7.1 | — |
+| ✅ Done | **Docker Compose + Caddy auto-TLS** | v0.7.1 | — |
 | ✅ Done | **Vector search for large documents** (FAISS + sentence-transformers) | v0.7.0 | — |
 | ✅ Done | **OCR for scanned PDF manuals** (Tesseract) | v0.7.0 | — |
 | ✅ Done | **DOCX diagnostic reports** (python-docx) | v0.7.0 | — |

docker-compose.yml

@@ -0,0 +1,45 @@
+# Docker Compose for HTTPS deployment (e.g. Microsoft Copilot Studio)
+#
+# Usage:
+#   1. Edit Caddyfile: replace mcp.example.com with your domain
+#   2. docker compose up -d
+#   3. Caddy auto-provisions a TLS certificate via Let's Encrypt
+#   4. Connect Copilot Studio to: https://mcp.example.com/sse
+#
+# For local testing (no TLS):
+#   docker compose up mcp-server
+#   → http://localhost:8000/sse
+
+services:
+  mcp-server:
+    build: .
+    restart: unless-stopped
+    environment:
+      - MCP_TRANSPORT=sse
+      - MCP_HOST=0.0.0.0
+      - MCP_PORT=8000
+    ports:
+      - "8000:8000"   # remove this line when using caddy
+    volumes:
+      - ./data:/app/data:ro
+      - ./resources:/app/resources:ro
+      - ./models:/app/models
+      - ./reports:/app/reports
+
+  # Uncomment below for production HTTPS via Caddy
+  # caddy:
+  #   image: caddy:2-alpine
+  #   restart: unless-stopped
+  #   ports:
+  #     - "80:80"
+  #     - "443:443"
+  #   volumes:
+  #     - ./Caddyfile:/etc/caddy/Caddyfile:ro
+  #     - caddy_data:/data
+  #     - caddy_config:/config
+  #   depends_on:
+  #     - mcp-server
+
+# volumes:
+#   caddy_data:
+#   caddy_config: