ncp
Verified Safeby portel-dev
Overview
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.
Installation
node dist/index-mcp.js --profile allEnvironment Variables
- NCP_WORKING_DIR
- NCP_PROFILE
- NCP_DEBUG
- NCP_ENABLE_SCHEDULE_MCP
- NCP_ENABLE_MCP_MANAGEMENT
- NCP_CLI_AUTOSCAN
- NCP_CONFIRM_BEFORE_RUN
- NCP_ENABLE_LOG_ROTATION
Security Notes
The "Code-Mode" feature (`ncp:code`) allows arbitrary TypeScript code execution within a `vm` sandbox. While this provides a degree of isolation, it's an inherently powerful capability. Users should exercise caution and ensure they only execute trusted code. The system implements a robust "Confirm-Before-Run" feature, using vector-based similarity to identify and prompt for confirmation on potentially dangerous operations (e.g., file writes, shell commands, API calls with side effects). This significantly enhances safety. MCP command arguments are validated to prevent common shell injection attacks. Sensitive credentials (API keys, tokens) are stored securely using a platform-native credential store, preventing them from being exposed in configuration files or logs.
Similar Servers
mcphub
A hub for managing, orchestrating, and providing a unified API for various Model Context Protocol (MCP) servers and their tools, including user management, OAuth services, and discovery of external servers.
tmcp
Build Model Context Protocol (MCP) servers for AI agents, providing schema-agnostic tools, resources, and prompts, with optional OAuth 2.1 authentication and distributed session management.
aicode-toolkit
Acts as an MCP proxy server to connect AI agents to multiple underlying MCP servers through a single connection, enabling progressive tool discovery and reducing initial token usage for tool descriptions.
1xn-vmcp
An open-source platform for composing, customizing, and extending multiple Model Context Protocol (MCP) servers into a single logical, virtual MCP server, enabling fine-grained context engineering for AI workflows and agents.