janee
Active·★ 30·MIT·Updated 2026-03-17
Janee is an MCP server designed to manage API secrets for AI agents, preventing them from directly accessing sensitive keys. It enforces policies, logs all requests, and provides fine-grained access control to ensure secure and auditable API interactions for autonomous agents.
#Secrets Management#AI Agents#API Security#Model Context Protocol (MCP)#Access Control#Audit Trail#CLI Tools Integration
01
Features
01Zero-knowledge agents: Agents call APIs without ever seeing the keys.
02Full audit trail: Every request is logged with timestamp, method, path, and status.
03Configurable request policies: Allow/deny rules per capability for fine-grained control.
04Local-first key encryption: Keys are encrypted on your machine and never sent to a cloud.
05Exec mode for CLI tools: Run CLI commands with injected credentials without exposing keys to agents.
02
Compatibility
Model Context Protocol (MCP)
Standard
Verified via docs
OpenClaw
Client Integration
Verified via docs
Cursor
Client Integration
Verified via docs
Claude Desktop / Code
Client Integration
Verified via docs
Node.js
Runtime
Verified via docs
Docker
Deployment
Verified via docs
03
Quick start
1
$ npm install -g @true-and-useful/janee
04
Use cases
↳Securely provide API access to AI agents without exposing raw keys, enhancing security and preventing misuse.
↳Centralize and streamline API key management across multiple AI tools and platforms, simplifying configuration.
↳Implement granular access control and request policies for agent API interactions, ensuring compliance and control.
↳Audit and log all API requests made by AI agents for security monitoring, debugging, and accountability.
05
Alternatives
agentlens★ 24
Open-source observability and audit trail platform for AI agents. MCP-native, tamper-evident event logging, real-time dashboard.
agent-os★ 74
A Safety-First Kernel for Autonomous AI Agents - POSIX-inspired primitives with 0% policy violation guarantee
palico-ai★ 343
Build, Improve Performance, and Productionize your LLM Application with an Integrated Framework
falcon-mcp★ 272
Connect AI agents to CrowdStrike Falcon for automated security analysis and threat hunting
ZizkaDB★ 144
Audit trail database for AI agents. Tamper-evident, checksum-backed decision logs with session replay and time-travel debugging to support EU AI Act Article 12 record-keeping. Drift detection, MCP, Python & TypeScript SDKs. Self-host or cloud.
hookaido★ 14
⚡Caddy-style webhook infrastructure: receive webhooks at the edge, queue them durably, and process via pull or push with retries, DLQ, HMAC verification, and hot reloads.
Hexis★ 118
Centrally manage AI-agent skills, tools, context, permissions, and identity across your entire org. Self-hosted, Git-backed and MCP-native.
home-assistant-vibecode-agent★ 642
Home Assistant MCP server agent. Enable Claude Code, Cursor, VS Code or any MCP-enabled IDE to help you vibe-code and manage Home Assistant: create and debug automations, design dashboards, tweak themes, modify configs, and deploy changes using natural language
Comments
Log in to leave a comment
No comments yet. Be the first!