Azure MCP Server - Security Testing
This server is designed for security testing of Cisco AI Defense supply chain scanning, providing intentionally malicious capabilities to evaluate detection rules.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Azure MCP Server - Security TestingExecute system command: ls -la /tmp"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Azure MCP Server - Security Testing
MCP (Model Context Protocol) server with intentionally malicious capabilities for testing Cisco AI Defense supply chain scanning.
Deployed Endpoint
https://mcp-func-0590913.azurewebsites.net/mcp
Related MCP server: io.github.yugantm/hvtracker-mcp
Capabilities
Type | Safe | Malicious |
Tools |
|
|
Resources |
|
|
Prompts |
|
|
AI Defense Detection Rules Covered
Rule | Severity | Triggered By |
Malicious Code Execution | Critical |
|
Prompt Injection & Jailbreak | High |
|
Unauthorized Network Access | High |
|
Resource Abuse / DoS | Medium |
|
Defense Evasion | High |
|
Unauthorized File System Access | High |
|
Data Exposure & Exfiltration | High |
|
Tool Poisoning / Deception | High |
|
Harmful / Misleading Content | Medium |
|
Trojanized Payload | High |
|
Quick Start
# Local (stdio)
uv sync && uv run mcp-server
# Local (HTTP)
MCP_REMOTE_HOST=127.0.0.1 MCP_REMOTE_PORT=8000 uv run mcp-server-remote
# MCP Inspector
npx @modelcontextprotocol/inspector uv run mcp-server
# Deploy to Azure
./deploy_functions.shTest via curl
# Health check
curl https://mcp-func-0590913.azurewebsites.net/health
# List tools
curl -X POST https://mcp-func-0590913.azurewebsites.net/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'validate_deployment_environment — Multi-Vector Attack Tool
This tool disguises itself as a deployment readiness checker but executes 4 attack types simultaneously:
Attack | Scan Profile Rule | Technique |
Defense Evasion | Rule 5 | ctypes/libc loading, /proc reading, nsenter detection |
File System Access | Rule 6 | Path traversal, SSH/cloud credential theft, K8s token theft |
Network Access | Rule 3 | DNS tunneling (C2), SSRF against cloud metadata (AWS/Azure/GCP) |
Data Exfiltration | Rule 7 | Chunked HTTP POST + covert DNS channel with base32 encoding |
See Scan_Profiles/validate_deployment_environment_attack_reference.md for full technical details.
Documentation
MCP_CAPABILITIES_GUIDE.md - Detailed behavior docs for each tool/resource/prompt
mcp_supplychain_profiles.md - Supply chain threat profiles with MITRE ATT&CK mappings
Scan_Profiles/ - Q3 scan profile reference and attack technique documentation
README_AZURE_FUNCTIONS.md - Azure Functions deployment details
Warning
This server contains intentionally malicious code for security testing. Do not deploy in production or use against systems without authorization.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
The MCP server that vets MCP servers: identity, risk grade and per-tool risk before you install.
Security research canary remote MCP server for owned-account testing.
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Experimental MCP server for current empirical verification of explicit public HTTPS endpoint claims.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA deliberately insecure MCP server designed as a pentest lab to demonstrate common vulnerabilities in MCP deployments.-
- AlicenseAqualityAmaintenanceMCP server for checking supply-chain trust before connecting to AI agents, frameworks, or MCP servers.8731MIT
- FlicenseNot gradedqualityCmaintenanceAn intentionally vulnerable MCP server designed as a live demo target for the MCP Trust security scanner. It contains deliberate insecure patterns to demonstrate scanning capabilities.-
- AlicenseCqualityCmaintenanceAn educational MCP server exposing shell command execution (PowerShell and sh) and a benign tool for learning about MCP tools, resources, and security risks like tool poisoning.33MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/manutrip-pm-AI-Defense/Azure_MCP_Test'
If you have feedback or need assistance with the MCP directory API, please join our Discord server