Infer

关于

Infer is a Model Context Protocol (MCP) server designed to bridge AI Copilot tools, such as GitHub Copilot and Cursor, with external computing and data resources. It facilitates secure and controlled access to SSH environments for command execution and PostgreSQL databases for querying. The server enforces strict policies, including command allowlists, output quotas, statement patterns, and concurrency limits, ensuring that AI tools operate within predefined boundaries. It also supports orchestration of tasks like classifier training via SSH profiles, making it a robust solution for managing AI-driven interactions with external systems.

主要功能

• Secure SSH command execution with configurable allowlists, output quotas, and runtime limits
• Policy-enforced PostgreSQL database querying with statement patterns, row limits, and connection restrictions
• Per-profile concurrency limits with cancellation support and progress notifications
• Orchestration of classifier training via defined SSH profiles
• Flexible configuration via JSON, supporting environment variables and secret file paths for credentials
• 0 GitHub stars

使用案例

• Integrating AI Copilots with remote servers for code execution and system interaction
• Enabling AI tools to query and retrieve data from PostgreSQL databases securely
• Automating and managing machine learning model training jobs via AI assistant commands