mcp-front

Tool

Auth proxy for Model Context Protocol servers - adds authentication to MCP tools for Claude.ai, Claude Code, Cursor,...

Copy the install, test the workflow, then decide if it earns a permanent slot.

Why nowStill in play

Still active enough to matter. Good candidate for a fast stack test instead of a long evaluation loop.

DecisionKeep on the radar

Copy the install, test the workflow, then decide if it earns a permanent slot.

Trial costFast eval

You can test this quickly and remove it cleanly if it misses.

Risk50/100

GitHub health 37/100. no security policy. 1 open issues make this testable, but not something to trust blind.

What You Are Adopting

AI Agent

Multiple

Model

Claude

One command inClean rollbackLow commitment

SandboxedInstalls to ~/.claude — isolated from your projects. One command to remove.

Fastest way to find out if mcp-front belongs in your setup.

Copy the install command, run a real test, and back it out cleanly if it slows you down.

Try now

git clone https://github.com/stainless-api/mcp-front ~/.claude/commands/mcp-front

Run this first. You will know quickly if the workflow earns a permanent slot.

Back out

rm -rf ~/.claude/commands/mcp-front

No messy cleanup loop. If it misses, remove it and keep moving.

Install Location

~/  └─ .claude/      ├─ commands/      │   └─ mcp-front/ ← installs here      ├─ agents/      └─ settings.json

Auth proxy for Model Context Protocol servers - adds authentication to MCP tools for Claude.ai, Claude Code, Cursor, Gemini

AgingLast commit 1mo ago

1open issues

Submitted April 29, 2026