Iris is an open-source MCP server that evaluates the output quality of AI agents, detects safety failures, and manages cost budgets. It integrates automatically with any MCP-compatible agent without requiring code changes.
From the registry: The agent eval standard for MCP. Score every agent output for quality, safety, and cost.
Please install the `mcp-server-iriseval` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js 20+** — Node.js runtime
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["@iris-eval/mcp-server"]
- optional environment variables:
- `IRIS_LOG_LEVEL`: Logging level (example: `info`)
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.IRIS_API_KEYrequiredAPI key for HTTP authentication.Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
Validate oh-my-posh configurations and segment snippets against the official schema.