加载中…
Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.
Iris 是 ChatHome Skills 收录的 MCP 条目，来源为 Official MCP Registry，质量分 78/100。 作为 Model Context Protocol 服务器，它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具，让 agent 的能力超出模型内置范围。 该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录，每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。 质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势，完整算法说明见来源页。安装命令已列于上方，可直接复制使用。 在将 Iris 加入生产 agent 工作流前，请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。
npx -y @iris-eval/mcp-server@0.21.0运行此命令前，请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-25T21:36:56.554987Z",
"publishedAt": "2026-10-25T21:36:56.554987Z",
"statusChangedAt": "2026-10-25T21:36:56.554987Z"
}
},
"server": {
"name": "io.github.iris-eval/mcp-server",
"icons": [
{
"src": "https://iris-eval.com/iris-logo.svg",
"sizes": [
"any"
],
"mimeType": "image/svg+xml"
},
{
"src": "https://iris-eval.com/iris-logo-white-bg.png",
"sizes": [
"180x180"
],
"mimeType": "image/png"
}
],
"title": "Iris",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "0.21.0",
"packages": [
{
"version": "0.21.0",
"transport": {
"type": "stdio"
},
"identifier": "@iris-eval/mcp-server",
"registryType": "npm",
"environmentVariables": [
{
"name": "IRIS_API_KEY",
"format": "string",
"isSecret": true,
"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",
"format": "string",
"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",
"format": "string",
"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",
"format": "string",
"description": "SQLite database path"
},
{
"name": "IRIS_SQLITE_DRIVER",
"format": "string",
"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",
"format": "string",
"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",
"format": "string",
"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",
"format": "string",
"description": "Log level: debug, info, warn, error"
},
{
"name": "IRIS_HOME",
"format": "string",
"description": "Directory for the database, custom rules and preferences (default ~/.iris)"
},
{
"name": "IRIS_ANTHROPIC_API_KEY",
"format": "string",
"isSecret": true,
"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",
"format": "string",
"isSecret": true,
"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",
"format": "string",
"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",
"format": "string",
"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",
"format": "string",
"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",
"format": "string",
"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",
"format": "string",
"description": "Relevance judge calls one request may make (default 20)"
},
{
"name": "IRIS_RELEVANCE_JUDGE_REDACT",
"format": "string",
"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",
"format": "boolean",
"description": "Let verify_citations fetch URLs (off by default); a tool argument can turn it off for a call, never on"
},
{
"name": "IRIS_DASHBOARD",
"format": "boolean",
"description": "Start the dashboard alongside the server (same as --dashboard)"
},
{
"name": "IRIS_DASHBOARD_PORT",
"format": "number",
"description": "Dashboard port (default 6920); IRIS_PORT is the MCP HTTP transport port (default 3000)"
},
{
"name": "IRIS_PORT",
"format": "number",
"description": "MCP HTTP transport port (default 3000); only used with --transport http"
},
{
"name": "IRIS_OTEL_ENDPOINT",
"format": "string",
"description": "OTLP/HTTP collector URL; when set, every stored trace is also exported as OpenTelemetry spans (best-effort, asynchronous)"
},
{
"name": "IRIS_CITATION_DOMAINS",
"format": "string",
"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",
"format": "string",
"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",
"format": "string",
"description": "Transport: stdio (default) or http; same as --transport"
},
{
"name": "IRIS_HOST",
"format": "string",
"description": "Bind host for the HTTP transport (default 127.0.0.1); only used with --transport http"
},
{
"name": "IRIS_ALLOWED_ORIGINS",
"format": "string",
"description": "Comma-separated Origin allowlist for the HTTP transport and dashboard CORS (default http://localhost:*)"
},
{
"name": "IRIS_MAX_INPUT_ELEMENTS",
"format": "number",
"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",
"format": "number",
"description": "The name of IRIS_MAX_INPUT_ELEMENTS before 0.21.0, read when the new name is unset"
},
{
"name": "IRIS_DASHBOARD_HOST",
"format": "string",
"description": "Bind host for the dashboard (default 127.0.0.1); same as --dashboard-host"
},
{
"name": "IRIS_OTEL_HEADERS",
"format": "string",
"description": "Comma-separated key=value headers sent with every OTLP export (for example an auth token for your collector)"
},
{
"name": "IRIS_OTEL_SERVICE_NAME",
"format": "string",
"description": "service.name resource attribute on exported spans (default iris-eval)"
},
{
"name": "IRIS_OTEL_TIMEOUT_MS",
"format": "number",
"description": "Timeout in milliseconds for each OTLP export request"
},
{
"name": "IRIS_WEBHOOK_URL",
"format": "string",
"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",
"format": "string",
"isSecret": true,
"description": "The signing key of that webhook (any string, or whsec_ + base64); the iris format refuses to run without one"
}
]
},
{
"version": "0.21.0",
"transport": {
"type": "stdio"
},
"fileSha256": "bf9c40dd660283ccade5a2205c0b5cb4ab78602e396bb53414b819e32de6a9c7",
"identifier": "https://github.com/iris-eval/mcp-server/releases/download/v0.21.0/iris-eval.mcpb",
"registryType": "mcpb"
}
],
"repository": {
"url": "https://github.com/iris-eval/mcp-server",
"source": "github"
},
"websiteUrl": "https://iris-eval.com",
"description": "Stop shipping agents on vibes. Score every agent output for quality, safety, and cost."
}
}