Mcp Server — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mcp Server (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A Model Context Protocol (MCP) server providing tool interfaces for legal information queries, weather data, Azure pricing, and utility functions.
This server offers API tools that can be used by Microsoft Copilot or other AI assistants supporting the MCP protocol:
git clone <repository-url>
cd mcp-server python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate pip install -r requirements.txtFor the Chinese character counting function:
cd functionpython mcp-server.py --host 0.0.0.0 --port 8080The server will run at http://localhost:8080.
/sse - Server-Sent Events endpoint/messages/ - MCP message processing endpoint# Query criminal law
Please look up Article 133 of the Criminal Law.
# Check weather
Are there any weather alerts in New York?
# Count Chinese characters
How many Chinese characters are in: 人工智能正在改变我们的生活方式。docker build -t mcp-server .docker run -p 8080:8080 --env-file .env mcp-serveraz login
az group create --name myResourceGroup --location eastasia
az acr create --resource-group myResourceGroup --name myacrregistry --sku Basic
az acr login --name myacrregistry
docker tag mcp-server myacrregistry.azurecr.io/mcp-server:latest
docker push myacrregistry.azurecr.io/mcp-server:latestaz containerapp env create \
--name my-environment \
--resource-group myResourceGroup \
--location eastasia
az containerapp create \
--name mcp-server-app \
--resource-group myResourceGroup \
--environment my-environment \
--image myacrregistry.azurecr.io/mcp-server:latest \
--registry-server myacrregistry.azurecr.io \
--target-port 8080 \
--ingress external \
--env-vars MONGODB_CONNECTION_STRING=secretref:mongodbconnection \
AZURE_OPENAI_API_KEY=secretref:azureopenaikeyaz appservice plan create --name myAppServicePlan \
--resource-group myResourceGroup \
--sku B1 \
--is-linux
az webapp create \
--resource-group myResourceGroup \
--plan myAppServicePlan \
--name my-mcp-server-app \
--deployment-container-image-name myacrregistry.azurecr.io/mcp-server:latest
az webapp config appsettings set \
--resource-group myResourceGroup \
--name my-mcp-server-app \
--settings MONGODB_CONNECTION_STRING=your_mongodb_connection_string \
AZURE_OPENAI_API_KEY=your_azure_openai_api_key
az webapp config container set \
--resource-group myResourceGroup \
--name my-mcp-server-app \
--docker-registry-server-url https://myacrregistry.azurecr.io \
--docker-custom-image-name myacrregistry.azurecr.io/mcp-server:latestThis project uses GitHub Actions to build Docker images and publish them to Azure Container Registry. See .github/workflows/action-to-acr.yml for details.
For production:
@mcp.tool()
async def my_new_tool(param1: str, param2: int = None) -> str:
"""Tool description.
Args:
param1: Description of parameter 1
param2: Description of parameter 2
"""
try:
# Your code here
return "Result"
except Exception as e:
return f"Error: {str(e)}"# Container Apps logs
az containerapp logs show --name mcp-server-app --resource-group myResourceGroup
# Web App logs
az webapp log tail --name my-mcp-server-app --resource-group myResourceGroup
# Function logs
az functionapp log tail --name haxufunctions --resource-group myResourceGroup~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.