Azure SFI Agent - MCP Server
An intelligent Model Context Protocol (MCP) server for deploying Azure resources with automatic SFI compliance orchestration.
Features
- 🚀 Interactive Deployment: Agent prompts for missing parameters
- 🔒 Automatic NSP Attachment: Network Security Perimeter for storage, key vault, cosmos-db, sql-db
- 📊 Automatic Log Analytics: Diagnostic settings for monitoring-enabled resources
- ✅ SFI Compliance: Enforced security baselines and governance
- 🎯 Zero Bypass: All deployments go through compliance orchestration
Installation
Via uvx (Recommended for GitHub Copilot)
uvx install azure-sfi-agent
Via pip
pip install azure-sfi-agent
Quick Start
1. Configure in GitHub Copilot (VS Code)
Add to your VS Code settings.json:
{
"github.copilot.mcpServers": {
"azure-sfi-agent": {
"command": "uvx",
"args": ["azure-sfi-agent"]
}
}
}
Or if installed via pip:
{
"github.copilot.mcpServers": {
"azure-sfi-agent": {
"command": "python",
"args": ["-m", "azure_sfi_agent.server"]
}
}
}
2. Login to Azure
az login
3. Use in Copilot Chat
User: "Create a storage account for ADLS"
Agent: 📋 Creating storage-account - Please provide:
✓ resource_group: (Azure resource group name)
✓ storageAccountName: (required)
✓ location: (required)
✓ accessTier: (required)
User: "RG: my-rg, name: datalake001, location: eastus, tier: Hot"
Agent: ✅ Deployment succeeded
✅ NSP attached: my-rg-nsp
Endpoints:
- DFS: https://datalake001.dfs.core.windows.net/
Supported Resources
| Resource Type | NSP | Log Analytics |
|---|---|---|
| storage-account (ADLS) | ✅ | ❌ |
| key-vault | ✅ | ✅ |
| cosmos-db | ✅ | ❌ |
| sql-db | ✅ | ❌ |
| openai | ❌ | ❌ |
| ai-search | ❌ | ✅ |
| ai-foundry | ❌ | ✅ |
| log-analytics | ❌ | ❌ |
Available Tools
create_azure_resource()- Interactive resource creation with compliancelist_permissions()- View active role assignmentslist_resources()- View accessible Azure resourcescreate_resource_group()- Create resource group with taggingget_bicep_requirements()- Check required parameters for a resource type
Requirements
- Python 3.10+
- Azure CLI installed and authenticated
- PowerShell Core (pwsh) for script execution
- Appropriate Azure RBAC permissions (Contributor role)
License
MIT
Support
For issues and questions, please visit the GitHub repository.
1 maintainer
Metadata
1 maintainer
Release files for azure-sfi-agent 1.0.40
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| azure_sfi_agent-1.0.40.tar.gz | 25.6 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| azure_sfi_agent-1.0.40-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 60.4 kB
Release files / azure_sfi_agent-1.0.40.tar.gz
| Download URL | azure_sfi_agent-1.0.40.tar.gz |
|---|---|
| Size | 25.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
44702872dde2018f2f8ba352b9a9b0e241743bed676053c2a09bdb57a09de622
|
|
BLAKE2b-256 checksum How to use checksums |
05f21fa10f87044811ae5b207d41c2d1d6400ecf404803598e7b87e7aab9266a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.11
|
Release files / azure_sfi_agent-1.0.40-py3-none-any.whl
| Download URL | azure_sfi_agent-1.0.40-py3-none-any.whl |
|---|---|
| Size | 34.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a5bf990d5e64fc6df7337e4941801987b9b7b8153dc3ac6190770f3678d1c3d9
|
|
BLAKE2b-256 checksum How to use checksums |
27a0f6b027dd42226b75b1834d396ba342bfa32adce84243f50f7785e98c4b01
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.11
|
Security for azure-sfi-agent 1.0.40
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
