Skip to content

rsdouglas/janee

v0.2.1 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 3mo Secrets & Credentials
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-agents api-keys claude cursor llm mcp
+4 more
mcp-server model-context-protocol secrets-management security

Summary

AI summary

Fixed CLI UX for service account credentials by adding file path input and related flags.

Full changelog

🐛 Bug Fix

Service Account File Input - Fixed CLI UX for service account credentials (#5)

Problem

Pasting multi-line service account JSON into the terminal failed because private keys contain newlines that got mangled during paste.

Solution

CLI now prompts for a file path instead of pasting JSON content:

Interactive:

janee add
# 📄 Path to service account JSON file: ~/Downloads/service-account.json

Non-interactive:

janee add google-analytics \
  --base-url https://analyticsdata.googleapis.com \
  --auth-type service-account \
  --credentials-file ~/Downloads/service-account.json \
  --scope https://www.googleapis.com/auth/analytics.readonly

Changes

  • Added --credentials-file flag for file path input
  • Added --auth-type flag for non-interactive usage
  • Added --scope flag (repeatable) for OAuth scopes
  • Supports ~ expansion to home directory
  • Better error messages for missing/invalid files

Installation

npm install -g @true-and-useful/[email protected]

Full Changelog: https://github.com/rsdouglas/janee/compare/v0.2.0...v0.2.1

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track rsdouglas/janee

Get notified when new releases ship.

Sign up free

About rsdouglas/janee

Self-evolving MCP server that generates and improves its own tools at runtime. Built on FastMCP, Janee uses LLM-driven tool generation to dynamically create, test, and refine MCP tools from natural language descriptions — enabling AI agents to extend their own capabilities on the fly.

All releases →

Beta — feedback welcome: [email protected]