{
  "slug": "io-github-iris-eval-mcp-server",
  "name": "io.github.iris-eval/mcp-server",
  "title": "Iris",
  "description": "Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.",
  "version": "0.21.0",
  "publishedAt": "2026-10-25T21:36:56.554987Z",
  "updatedAt": "2026-10-25T21:36:56.554987Z",
  "repoUrl": "https://github.com/iris-eval/mcp-server",
  "websiteUrl": "https://iris-eval.com",
  "namespace": {
    "type": "github",
    "owner": "iris-eval"
  },
  "kind": "local",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "@iris-eval/mcp-server",
      "version": "0.21.0",
      "transport": "stdio",
      "runtimeHint": null
    },
    {
      "registryType": "mcpb",
      "identifier": "https://github.com/iris-eval/mcp-server/releases/download/v0.21.0/iris-eval.mcpb",
      "version": "0.21.0",
      "transport": "stdio",
      "runtimeHint": null
    }
  ],
  "remotes": [],
  "envVars": [
    {
      "name": "IRIS_API_KEY",
      "isSecret": true,
      "isRequired": false,
      "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"
    },
    {
      "name": "IRIS_API_KEY_FILE",
      "isSecret": false,
      "isRequired": false,
      "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",
      "isSecret": false,
      "isRequired": false,
      "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",
      "isSecret": false,
      "isRequired": false,
      "description": "SQLite database path"
    },
    {
      "name": "IRIS_SQLITE_DRIVER",
      "isSecret": false,
      "isRequired": false,
      "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",
      "isSecret": false,
      "isRequired": false,
      "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",
      "isSecret": false,
      "isRequired": false,
      "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",
      "isSecret": false,
      "isRequired": false,
      "description": "Log level: debug, info, warn, error"
    },
    {
      "name": "IRIS_HOME",
      "isSecret": false,
      "isRequired": false,
      "description": "Directory for the database, custom rules and preferences (default ~/.iris)"
    },
    {
      "name": "IRIS_ANTHROPIC_API_KEY",
      "isSecret": true,
      "isRequired": false,
      "description": "Enables evaluate_with_llm_judge and verify_citations with an Anthropic model. Optional: the deterministic rules never need a key"
    },
    {
      "name": "IRIS_OPENAI_API_KEY",
      "isSecret": true,
      "isRequired": false,
      "description": "Enables evaluate_with_llm_judge and verify_citations with an OpenAI model. Optional: the deterministic rules never need a key"
    },
    {
      "name": "IRIS_LLM_JUDGE_MAX_COST_USD_PER_EVAL",
      "isSecret": false,
      "isRequired": false,
      "description": "Hard cap on the worst-case cost of one LLM judge call (default 0.25); max_cost_usd can lower it for a call, never raise it"
    },
    {
      "name": "IRIS_RELEVANCE_JUDGE_MODEL",
      "isSecret": false,
      "isRequired": false,
      "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_LLM_JUDGE_DAILY_BUDGET_USD",
      "isSecret": false,
      "isRequired": false,
      "description": "What every judge call together may spend per UTC day, per tenant, in USD (default 1): the relevance judge, evaluate_with_llm_judge and verify_citations. Past it no judge call is made"
    },
    {
      "name": "IRIS_RELEVANCE_JUDGE_DAILY_BUDGET_USD",
      "isSecret": false,
      "isRequired": false,
      "description": "The name of IRIS_LLM_JUDGE_DAILY_BUDGET_USD before 0.21.0. Read when the new name is unset, and it then limits every judge call"
    },
    {
      "name": "IRIS_RELEVANCE_JUDGE_MAX_CALLS_PER_REQUEST",
      "isSecret": false,
      "isRequired": false,
      "description": "Relevance judge calls one request may make (default 20)"
    },
    {
      "name": "IRIS_RELEVANCE_JUDGE_REDACT",
      "isSecret": false,
      "isRequired": false,
      "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",
      "isSecret": false,
      "isRequired": false,
      "description": "Let verify_citations fetch URLs (off by default); a tool argument can turn it off for a call, never on"
    },
    {
      "name": "IRIS_DASHBOARD",
      "isSecret": false,
      "isRequired": false,
      "description": "Start the dashboard alongside the server (same as --dashboard)"
    },
    {
      "name": "IRIS_DASHBOARD_PORT",
      "isSecret": false,
      "isRequired": false,
      "description": "Dashboard port (default 6920); IRIS_PORT is the MCP HTTP transport port (default 3000)"
    },
    {
      "name": "IRIS_PORT",
      "isSecret": false,
      "isRequired": false,
      "description": "MCP HTTP transport port (default 3000); only used with --transport http"
    },
    {
      "name": "IRIS_OTEL_ENDPOINT",
      "isSecret": false,
      "isRequired": false,
      "description": "OTLP/HTTP collector URL; when set, every stored trace is also exported as OpenTelemetry spans (best-effort, asynchronous)"
    },
    {
      "name": "IRIS_CITATION_DOMAINS",
      "isSecret": false,
      "isRequired": false,
      "description": "Comma-separated domain allowlist for verify_citations fetches (only consulted when IRIS_CITATION_ALLOW_FETCH is on); a tool argument can narrow it, never add to it"
    },
    {
      "name": "IRIS_CITATION_MAX_COST_USD_TOTAL",
      "isSecret": false,
      "isRequired": false,
      "description": "The most one verify_citations call may spend on judge calls, in USD (default 1); max_cost_usd_total can lower it, never raise it"
    },
    {
      "name": "IRIS_TRANSPORT",
      "isSecret": false,
      "isRequired": false,
      "description": "Transport: stdio (default) or http; same as --transport"
    },
    {
      "name": "IRIS_HOST",
      "isSecret": false,
      "isRequired": false,
      "description": "Bind host for the HTTP transport (default 127.0.0.1); only used with --transport http"
    },
    {
      "name": "IRIS_ALLOWED_ORIGINS",
      "isSecret": false,
      "isRequired": false,
      "description": "Comma-separated Origin allowlist for the HTTP transport and dashboard CORS (default http://localhost:*)"
    },
    {
      "name": "IRIS_MAX_INPUT_ELEMENTS",
      "isSecret": false,
      "isRequired": false,
      "description": "The most array elements and object keys one input may hold before it is validated (default 100000): a tool call's arguments, and a dashboard or OTLP JSON request body. A tool call over it gets an error result; a body, 413. OTLP protobuf has its own ceiling, one element per 5 bytes of the request size limit"
    },
    {
      "name": "IRIS_MAX_TOOL_INPUT_ELEMENTS",
      "isSecret": false,
      "isRequired": false,
      "description": "The name of IRIS_MAX_INPUT_ELEMENTS before 0.21.0, read when the new name is unset"
    },
    {
      "name": "IRIS_DASHBOARD_HOST",
      "isSecret": false,
      "isRequired": false,
      "description": "Bind host for the dashboard (default 127.0.0.1); same as --dashboard-host"
    },
    {
      "name": "IRIS_OTEL_HEADERS",
      "isSecret": false,
      "isRequired": false,
      "description": "Comma-separated key=value headers sent with every OTLP export (for example an auth token for your collector)"
    },
    {
      "name": "IRIS_OTEL_SERVICE_NAME",
      "isSecret": false,
      "isRequired": false,
      "description": "service.name resource attribute on exported spans (default iris-eval)"
    },
    {
      "name": "IRIS_OTEL_TIMEOUT_MS",
      "isSecret": false,
      "isRequired": false,
      "description": "Timeout in milliseconds for each OTLP export request"
    },
    {
      "name": "IRIS_WEBHOOK_URL",
      "isSecret": false,
      "isRequired": false,
      "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",
      "isSecret": true,
      "isRequired": false,
      "description": "The signing key of that webhook (any string, or whsec_ + base64); the iris format refuses to run without one"
    }
  ],
  "category": "business",
  "subcategory": "prices",
  "company": "",
  "categoryAuto": true,
  "checks": [
    {
      "id": "source-linked",
      "label": "Source repository linked",
      "result": "pass",
      "detail": "https://github.com/iris-eval/mcp-server"
    },
    {
      "id": "version-pinned",
      "label": "Version pinned",
      "result": "pass",
      "detail": "Every package has an explicit version"
    },
    {
      "id": "secrets-requested",
      "label": "Secrets requested",
      "result": "warn",
      "detail": "Asks for 4 secrets: IRIS_API_KEY, IRIS_ANTHROPIC_API_KEY, IRIS_OPENAI_API_KEY, IRIS_WEBHOOK_SECRET"
    },
    {
      "id": "known-registry",
      "label": "Known package registry",
      "result": "pass",
      "detail": "All packages come from npm, PyPI, OCI, NuGet or MCPB"
    },
    {
      "id": "namespace",
      "label": "Namespace ownership",
      "result": "info",
      "detail": "Name verified via GitHub account iris-eval"
    },
    {
      "id": "meta-text",
      "label": "Registry text aimed at the AI",
      "result": "pass",
      "detail": "Description and settings contain no hidden characters or instructions to the AI"
    },
    {
      "id": "install-scripts",
      "label": "Install scripts",
      "result": "pass",
      "detail": "@iris-eval/mcp-server@0.21.0 runs nothing at install"
    },
    {
      "id": "code-flags",
      "label": "Code red flags",
      "result": "pass",
      "detail": "Read 529 files in @iris-eval/mcp-server@0.21.0: no obfuscation, encoded execution, credential reads or data-collection endpoints found"
    },
    {
      "id": "ai-text",
      "label": "Text aimed at the AI",
      "result": "warn",
      "detail": "Tells the AI to hide something from the user (dist/eval/text/directives.js: \"… user', 'do not mention this', 'without telling the user', 'send the contents to', 'post…\"). Read the context: a security tool may quote these on purpose."
    }
  ],
  "scannedAt": "2026-10-29",
  "level": "Scanned",
  "install": [
    {
      "label": "Claude Desktop (npm)",
      "kind": "claude_desktop_json",
      "text": "{\n  \"mcpServers\": {\n    \"mcp-server\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@iris-eval/mcp-server@0.21.0\"\n      ]\n    }\n  }\n}"
    }
  ],
  "curated": true,
  "stars": 9,
  "archived": false,
  "pushedAt": "2026-10-26T17:06:55Z",
  "health": {
    "score": 56,
    "parts": {
      "popularity": 0.38213144314849623,
      "activity": 0.6,
      "issues": 0.9090909090909091,
      "security": 0.6
    },
    "fail": 0,
    "warn": 2,
    "raw": {
      "stars": 9,
      "forks": 4,
      "downloads": 658,
      "hn": null,
      "issuesOpen": 6,
      "issuesClosed": 60,
      "prsMerged": 674,
      "commits90": 0,
      "release": "2026-10-25T21:36:43Z",
      "pushed": "2026-10-26T17:06:55Z",
      "growth": null,
      "growthDays": null,
      "archived": false
    },
    "at": "2026-10-31T07:35:52.424Z"
  },
  "icon": "/icons/s/io-github-iris-eval-mcp-server.png"
}