Inject credentials into proxied API requests with policy checks and audit logs.
npx skills add https://github.com/rsdouglas/janee --skill janee
Please help me install this Agent Skill. Skill: janee Source: https://github.com/rsdouglas/janee/tree/main Command: npx skills add https://github.com/rsdouglas/janee --skill janee
Janee addresses the risk of exposing API secrets to AI agents by acting as a local MCP-based proxy that injects credentials server-side and never reveals keys to agents.
Install Janee, run janee init to create a master key, add a service with janee add, and start the MCP server with janee serve so that agents can call execute() without ever seeing raw credentials.
High-intent search queries and answers about installing and using this skill.
To prevent API secret exposure, use a zero-knowledge proxy that injects credentials server-side so keys never reach AI agents. The proxy decrypts secrets per request, applies policy checks, and returns the API response without revealing raw credentials.
A zero-knowledge proxy for MCP credential injection is a local server that decrypts secrets and applies them to proxied API calls on the agent's behalf. It coordinates with MCP tools, enforces per-capability access rules, and maintains audit trails.
Install the proxy, run the initialization command to generate a master key, add your services, and start the MCP server. Agents can then call execute() to route requests through the proxy, which handles credential injection and policy enforcement.
Yes, you can run whitelisted local CLI tools using exec mode, which securely injects credentials into environment variables. The proxy enforces per-capability access rules and logs the event to maintain a full audit trail during execution.
Yes, the credential proxy works with GitHub, OpenAI, and AWS services across stdio and HTTP transports. It supports multi-agent integrations, applying per-capability access rules and audit logging to each proxied API request.
Access policies and audit trails for proxied API calls are managed through per-capability rules, TTLs, and ownership controls. The proxy logs each decrypted credential request, applies policy checks, and records the event before returning the API response.
tylerjrbuellManage Docker-backed MCP server lifecycle with transport auto-detection.
skwuwuVerify GVM audit log integrity and export compliance reports.
fabio-barbozaConsolidate MCP capability registry and dynamic discovery for do-* skills.
VincentChong123Configure container agents to use environment-based credentials instead of the OneCLI gateway vault.
