toolport
Reduces token overhead by 90% through lazy tool discovery, enforces tool isolation to prevent supply-chain compromise, and centralizes credential management …
Local-first MCP gateway. One port for every tool and every AI client: lazy discovery (~90% token savings), tool integrity + quarantine, secrets in the OS keychain.
- Manage API credentials securely without storing secrets in configuration files.
- Route AI tool requests through a single gateway to reduce token consumption.
- Quarantine untrusted tools to prevent unauthorized access to sensitive systems.
Reduces token overhead by 90% through lazy tool discovery, enforces tool isolation to prevent supply-chain compromise, and centralizes credential management via OS keychains—cutting operational friction and security debt in multi-tool AI deployments.
Platform engineers managing multiple AI clients and tool integrations who need centralized gateway control, compliance enforcement, and cost optimization.
https://github.com/tsouth89/toolport
By tsouth89
How to Get It
Download a prebuilt installer from https://github.com/tsouth89/toolport/releases (Windows/macOS/Linux; Linux users prefer the .deb).
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me manage API credentials securely without storing secrets in configuration files
Trust Signals Auto-scanned
Community Pulse Growing
Discussed on Hacker News
- Show HN: Unify – A single file Python CLI Tool port of repomix — Hacker News · 2 pts
1 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 56 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 56 GitHub stars; contributors unknown; last commit 0d ago; license MIT.