Iris MCP Setup & Guide

{
  "id": "io.github.iris-eval/mcp-server",
  "type": "mcp-server",
  "version": "0.20.0",
  "displayName": "Iris",
  "description": "Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.",
  "repository": {
    "url": "https://github.com/iris-eval/mcp-server",
    "source": "github"
  },
  "homepage": "https://iris-eval.com",
  "distribution": {
    "packages": [
      {
        "registryType": "npm",
        "identifier": "@iris-eval/mcp-server",
        "version": "0.20.0",
        "transport": "stdio",
        "environmentVariables": [
          {
            "name": "IRIS_API_KEY",
            "description": "API key for HTTP authentication. Required to bind the HTTP transport or the dashboard beyond loopback (0.0.0.0, a LAN address, a container): without it the server refuses to start",
            "isSecret": true
          },
          {
            "name": "IRIS_API_KEY_FILE",
            "description": "Path to a file whose trimmed contents are the API key (the secret-file pattern Docker and Kubernetes mount). Set this or IRIS_API_KEY, not both; further keys and rotation are security.apiKeys in config.json"
          },
          {
            "name": "IRIS_ALLOW_UNAUTHENTICATED",
            "description": "Set to 1 to run a non-loopback bind with NO API key on purpose (lifts the startup refusal; the network is then your boundary)"
          },
          {
            "name": "IRIS_DB_PATH",
            "description": "SQLite database path"
          },
          {
            "name": "IRIS_SQLITE_DRIVER",
            "description": "Which SQLite driver holds the database: native (better-sqlite3, the default) or node (Node's built-in node:sqlite, Node 22.13+). Unset: native, falling back to node when the native module cannot load"
          },
          {
            "name": "IRIS_SEARCH_BUDGET_MS",
            "description": "How long one trace search may read before it answers with the matches found so far, in milliseconds (50-60000, default 1000)"
          },
          {
            "name": "IRIS_SEARCH_INDEX",
            "description": "on (default) or off. off keeps no full-text index of the traces: writes are cheaper, and a search reads the traces within its time budget"
          },
          {
            "name": "IRIS_LOG_LEVEL",
            "description": "Log level: debug, info, warn, error"
          },
          {
            "name": "IRIS_HOME",
            "description": "Directory for the database, custom rules and preferences (default ~/.iris)"
          },
          {
            "name": "IRIS_ANTHROPIC_API_KEY",
            "description": "Enables evaluate_with_llm_judge and verify_citations with an Anthropic model. Optional: the deterministic rules never need a key",
            "isSecret": true
          },
          {
            "name": "IRIS_OPENAI_API_KEY",
            "description": "Enables evaluate_with_llm_judge and verify_citations with an OpenAI model. Optional: the deterministic rules never need a key",
            "isSecret": true
          },
          {
            "name": "IRIS_LLM_JUDGE_MAX_COST_USD_PER_EVAL",
            "description": "Hard cap on the worst-case cost of one judge or citation call (default 0.25)"
          },
          {
            "name": "IRIS_RELEVANCE_JUDGE_MODEL",
            "description": "A priced judge model; answers_the_ask then asks it on every evaluation with input, sending that input and output to the model's provider, and gates on its verdict (off by default)"
          },
          {
            "name": "IRIS_RELEVANCE_JUDGE_DAILY_BUDGET_USD",
            "description": "What the relevance judge may spend per UTC day, per tenant, in USD (default 1); past it answers_the_ask reads the ask lexically"
          },
          {
            "name": "IRIS_RELEVANCE_JUDGE_MAX_CALLS_PER_REQUEST",
            "description": "Relevance judge calls one request may make (default 20)"
          },
          {
            "name": "IRIS_RELEVANCE_JUDGE_REDACT",
            "description": "on (default) replaces the PII and credentials no_pii flags before the relevance judge sends input and output to its provider; off sends them as they are"
          },
          {
            "name": "IRIS_CITATION_ALLOW_FETCH",
            "description": "Let verify_citations fetch URLs (off by default)"
          },
          {
            "name": "IRIS_DASHBOARD",
            "description": "Start the dashboard alongside the server (same as --dashboard)"
          },
          {
            "name": "IRIS_DASHBOARD_PORT",
            "description": "Dashboard port (default 6920); IRIS_PORT is the MCP HTTP transport port (default 3000)"
          },
          {
            "name": "IRIS_PORT",
            "description": "MCP HTTP transport port (default 3000); only used with --transport http"
          },
          {
            "name": "IRIS_OTEL_ENDPOINT",
            "description": "OTLP/HTTP collector URL; when set, every stored trace is also exported as OpenTelemetry spans (best-effort, asynchronous)"
          },
          {
            "name": "IRIS_CITATION_DOMAINS",
            "description": "Comma-separated domain allowlist for verify_citations fetches (only consulted when IRIS_CITATION_ALLOW_FETCH is on)"
          },
          {
            "name": "IRIS_TRANSPORT",
            "description": "Transport: stdio (default) or http; same as --transport"
          },
          {
            "name": "IRIS_HOST",
            "description": "Bind host for the HTTP transport (default 127.0.0.1); only used with --transport http"
          },
          {
            "name": "IRIS_ALLOWED_ORIGINS",
            "description": "Comma-separated Origin allowlist for the HTTP transport and dashboard CORS (default http://localhost:*)"
          },
          {
            "name": "IRIS_DASHBOARD_HOST",
            "description": "Bind host for the dashboard (default 127.0.0.1); same as --dashboard-host"
          },
          {
            "name": "IRIS_OTEL_HEADERS",
            "description": "Comma-separated key=value headers sent with every OTLP export (for example an auth token for your collector)"
          },
          {
            "name": "IRIS_OTEL_SERVICE_NAME",
            "description": "service.name resource attribute on exported spans (default iris-eval)"
          },
          {
            "name": "IRIS_OTEL_TIMEOUT_MS",
            "description": "Timeout in milliseconds for each OTLP export request"
          },
          {
            "name": "IRIS_WEBHOOK_URL",
            "description": "The receiver of the webhook that fires on a moment (docs/webhooks.md); merged over notify.webhook in config.json"
          },
          {
            "name": "IRIS_WEBHOOK_SECRET",
            "description": "The signing key of that webhook (any string, or whsec_ + base64); the iris format refuses to run without one",
            "isSecret": true
          }
        ]
      },
      {
        "registryType": "mcpb",
        "identifier": "https://github.com/iris-eval/mcp-server/releases/download/v0.20.0/iris-eval.mcpb",
        "version": "0.20.0",
        "transport": "stdio"
      }
    ],
    "remotes": []
  },
  "dependencies": [],
  "installTargets": [
    "claude-code",
    "claude-desktop",
    "cursor",
    "vscode",
    "trae",
    "cherry-studio",
    "lingma",
    "windsurf",
    "cline",
    "workbuddy"
  ],
  "keywords": [],
  "provenance": {
    "origin": "official-mcp-registry",
    "originalId": "io.github.iris-eval/mcp-server",
    "originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.iris-eval%2Fmcp-server/versions/latest",
    "isOfficial": true,
    "status": "active"
  }
}