shinzo
by shinzo-labs
Overview
A complete observability platform for AI Agents and MCP servers, enabling ingestion and analysis of OpenTelemetry-compatible data.
Installation
docker-compose up --build -dEnvironment Variables
- DATABASE_URL
- BACKEND_PORT
- JWT_SECRET
- ENCRYPTION_KEY
- MAILGUN_API_KEY
- MAILGUN_DOMAIN
- FROM_EMAIL
- FROM_NAME
- FRONTEND_URL
- LOG_LEVEL
- MAX_PAYLOAD_SIZE
- RATE_LIMIT_MAX
- RATE_LIMIT_WINDOW
Security Notes
Critical security vulnerabilities exist due to hardcoded default secrets in `backend/src/config.ts` for `JWT_SECRET` and `ENCRYPTION_KEY`. These values are explicitly warned about (`default-secret-change-in-production`, `dev-fallback-key-change-in-prod`) but are present in the codebase. Deploying with these defaults would compromise user authentication and encrypted provider API keys. While SQL queries use parameterized binding to prevent injection, the key management is a significant flaw. `MAILGUN_API_KEY` also has a default empty string, which would lead to email failures if not configured.
Similar Servers
klavis
Creates an AI agent that uses Klavis Strata to interact with Gmail and YouTube through MCP, demonstrating how to summarize a YouTube video and email the summary.
mcp-gateway-registry
This MCP server provides programmatic interaction with the MCP Gateway Registry API, enabling management of registered services and AI agents, including registration, toggling, health monitoring, group-based access control, and intelligent (semantic) discovery of tools and agents.
mcp-server-datadog
Manages Datadog observability features including incidents, monitors, logs, dashboards, metrics, traces, hosts, and downtimes through an MCP server for LLMs.
mcpcat-typescript-sdk
MCPcat is an analytics platform designed for MCP server owners to capture user intentions and behavior patterns, offering session replay, trace debugging, and integration with existing observability tools.