MCP-Open-Discovery-with-AMQP
Verified Safeby nagual69
Overview
Production-ready infrastructure discovery and CMDB platform for AI assistants, automation, and enterprise infrastructure management, powered by 53 MCP SDK tools.
Installation
docker-compose up -dEnvironment Variables
- TRANSPORT_MODE
- HTTP_PORT
- AMQP_URL
- AMQP_USERNAME
- AMQP_PASSWORD
- ZABBIX_BASE_URL
- ZABBIX_USERNAME
- ZABBIX_PASSWORD
- MCP_CREDS_KEY
- OAUTH_ENABLED
- OAUTH_CLIENT_ID
- OAUTH_CLIENT_SECRET
- OAUTH_INTROSPECTION_ENDPOINT
- PLUGIN_ALLOW_RUNTIME_DEPS
- STRICT_INTEGRITY
- REQUIRE_SIGNATURES
- AMQP_AUTO_RECOVERY
- LOG_LEVEL
- PLUGINS_ROOT
- PLUGIN_TRUSTED_KEY_IDS
Security Notes
The project implements robust security controls for its dynamic plugin architecture, including manifest validation, SHA256 integrity checks of plugin distributions, optional digital signature verification using trusted keys, and configurable dependency policies (e.g., 'bundled-only', 'sandbox-required'). A runtime sandboxing mechanism intercepts core Node.js module imports and external dependencies during plugin loading, enforcing permissions and detecting dynamic code execution (`eval`, `new Function`). Command injection risks for external tools (Nmap, network tools) are mitigated by critical input sanitization functions. Secrets are managed securely using environment variables or an encrypted local store with key rotation. OAuth 2.1 middleware is implemented for API protection, including token introspection and scope validation. A potential risk for default configurations is the 'allow-all' CORS policy for HTTP, which should be restricted in production, and Nmap tools requiring 'privileged' container capabilities.
Similar Servers
terraform-mcp-server
The Terraform MCP Server provides seamless integration with Terraform Registry APIs and HCP Terraform/Terraform Enterprise, enabling AI assistants (LLMs) to generate high-quality Terraform code and automate IaC workflows.
tfmcp
A CLI tool enabling LLMs to interact with and manage Terraform infrastructure through the Model Context Protocol (MCP), offering advanced analysis and security features.
1xn-vmcp
An open-source tool for composing, customizing, and extending multiple Model Context Protocol (MCP) servers into a single logical, virtual MCP server, facilitating fine-grained context-engineering for AI workflows and agents.
ncp
A unified Model Context Protocol (MCP) orchestrator that enables semantic tool discovery, management, scheduling, and execution across a diverse ecosystem of connected AI tools and services.