Open-source gateway that securely connects AI agents to any API, with credential injection and NAT traversal.
NyxID is worth checking the docs before setup with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view ChronoAIProject/NyxID --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
Repository setup guidance
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 24 days ago.
36 GitHub stars indicate community interest.
40 open issues signal maintenance load.
Apache-2.0 license detected.
3 security/trust notes recorded.
Setup difficulty is 3/5.
Official MCP reference servers from Anthropic. Includes servers for filesystem, GitHub, Postgres, Slack, and more.
Zero-dependency, token-efficient MCP server for querying multiple databases via a single interface.
A secure MCP server for AI applications to interact with MySQL databases.
Up-to-date code documentation for LLMs and AI code editors, eliminating outdated or hallucinated API references.
NyxID is a tool that lets AI assistants like Claude Code or Cursor safely use your APIs. You store your API keys once, and NyxID automatically adds them to requests, so your AI never sees the raw keys. It can even reach services on your private network or localhost without opening ports.
NyxID is an open-source Agent Connectivity Gateway designed to bridge AI agents with any API, whether public, internal, or on localhost. It acts as a reverse proxy that automatically injects credentials, ensuring that raw API keys are never exposed to the AI agent. NyxID supports NAT traversal through credential nodes, allowing secure access to localhost services without VPN or port forwarding. It also wraps REST APIs as MCP (Model Context Protocol) tools, enabling seamless integration with MCP-compatible clients like Claude Code, Cursor, and VS Code. Key features include per-agent isolation with scoped tokens, OIDC/OAuth 2.0 with PKCE, RBAC, service accounts, transaction approval via Telegram and mobile push, and an LLM gateway for multiple providers. The project is written in Rust and TypeScript, with a React-based web console for managing services and configurations.
36
Stars
9
Forks
40
Issues
Apache-2.0
License
Open-source gateway that securely connects AI agents to any API, with credential injection and NAT traversal.
Developers building AI-powered applications that need secure API access., DevOps engineers managing API gateways and credential security., AI/ML engineers integrating MCP tools into their workflows.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Self-hosted solution requires proper security configuration to protect the gateway and stored credentials. NAT traversal and credential nodes introduce additional attack surface; ensure nodes are secured.
Similar or complementary options to evaluate include MCP Server Collection, dbhub, mysql_mcp_server.
Aug 20, 2026