@index9/mcp 6.3.0 → 6.5.0

package/dist/cli.js

@@ -224,7 +224,7 @@ Parameters:
 - providerSort: "throughput" | "price" | "latency" \u2014 opt-in OpenRouter provider routing. Defaults to OpenRouter's load-balanced choice.
 - providerOrder: ordered list of provider slugs (up to 8). Try these providers first before falling back. Useful for steering around an overloaded provider for a single model.
 - fallbackModels: ordered list of model ids (up to 5). OpenRouter automatically retries the request against the next id when the primary is unavailable. Use sparingly \u2014 a benchmark should usually test the model you asked for, not a substitute.
-- debug: When true, each result includes a \`debug\` field with the raw upstream finish_reason, error message, provider name, refusal, and usage. Use to diagnose "missing assistant text" without re-running.
+- debug: When true, each result includes a \`debug\` field with the raw upstream finish_reason, error message, \`providerName\` (OpenRouter routing/fulfillment provider \u2014 can differ from the publisher, e.g. an anthropic/* model served via Google Vertex), \`modelPublisher\` (derived from the canonical id prefix \u2014 e.g. "anthropic", "x-ai"), refusal, and usage. Use to diagnose "missing assistant text" without re-running.
 
 Results (live): each result carries modelId (the id you passed), resolvedModelId (canonical id, present when the input was an alias), ok, response, latencyMs, tokens { prompt, completion }, cost (USD; live from OpenRouter when available, else estimated from cached pricing), and truncated=true when finish_reason is "length". On failure, results include \`error\` (free-form) plus \`failureReason\` ("insufficient_credits" | "model_unavailable" | "rate_limited" | "capacity" | "timeout" | "invalid_request" | "unknown") so callers can pick a retry strategy without parsing the error string. \`capacity\` indicates the provider is overloaded \u2014 apply a longer backoff or set \`fallbackModels\` and retry. When \`debug: true\` is set, each result also carries a \`debug\` block with the upstream provider's diagnostic fields.
 
@@ -245,13 +245,16 @@ var PARAM_DESCRIPTIONS = {
   excludeFree: `When true, exclude models with id ending in ':free'. Useful for sortBy=price (which would otherwise be dominated by free-tier preview models) and when you want a paid SLA. Default false.`,
   requireKeywordMatch: `When true, suppress weak vector-only results from semantic queries. If no candidate has a BM25 keyword hit, returns an empty page with meta.confidence='low' and meta.lowConfidenceReason \u2014 instead of returning misleading nearest-neighbor matches. Filter-only queries (sortBy=created or sortBy=price without q) ignore this flag. Default false.`,
   expectedPromptTokens: `Expected number of prompt tokens for dryRun cost estimation. When set, overrides the heuristic that counts characters from the literal \`prompt\` string \u2014 use this for capacity planning ("what would 6000-token reviews cost?") without pasting filler. If both are omitted, the prompt string is tokenized at ~4 chars/token.`,
-  expectedCompletionTokens: `Expected number of completion tokens for cost estimation (default: 256). Typical ranges: 100-500 for quick tests, 1000-2000 for code generation, 4000+ for long-form content. This is a heuristic \u2014 actual billed tokens may differ.`
+  expectedCompletionTokens: `Expected number of completion tokens for cost estimation (default: 256). Typical ranges: 100-500 for quick tests, 1000-2000 for code generation, 4000+ for long-form content. This is a heuristic \u2014 actual billed tokens may differ.`,
+  minPrice: `Minimum effective prompt price in USD per million tokens. Matches the basis exposed in \`pricing.effectivePromptPerMillion\` and \`pageInfo.priceSortBasis\` \u2014 token price plus per-request fees scaled to per-million, so a model with $0.30/M tokens and a $0.30 per-request fee evaluates as $0.60/M effective. Models with no resolvable price (zero-token, no per-request fee, non-\`:free\` id) are excluded when this bound is set.`,
+  maxPrice: `Maximum effective prompt price in USD per million tokens. Matches the basis exposed in \`pricing.effectivePromptPerMillion\` and \`pageInfo.priceSortBasis\` \u2014 token price plus per-request fees scaled to per-million, so a model with $0.30/M tokens and a $0.30 per-request fee evaluates as $0.60/M effective and is excluded by \`maxPrice: 0.55\`. Models with no resolvable price (zero-token, no per-request fee, non-\`:free\` id) are excluded when this bound is set.`
 };
 var SITE = {
   nav: {
     brand: "index9",
     tools: "Tools",
     howItWorks: "How it works",
+    caseStudy: "Case study",
     install: "Install",
     faq: "FAQ",
     github: "GitHub",
@@ -259,19 +262,18 @@ var SITE = {
     installCta: "Install"
   },
   hero: {
-    titleLine1: "Pick the right AI model",
-    titleLine2: "from chat",
-    subtitle: "An MCP server your coding assistant uses to search, compare, and live-test 300+ models for the task you're on.",
+    title: "Pick AI models from live data, not your assistant's memory.",
+    subtitle: "An MCP server with five tools for Claude Code, Cursor, VS Code, and Codex. Search, compare, cost-model, and live-test 300+ models.",
     pricingNote: "Free. You only pay OpenRouter for live model calls.",
     seeHowItWorks: "See a real session",
     updatedBadge: "OpenRouter data \xB7 refreshed ",
-    panel: {
-      signalEyebrow: "Just landed",
-      signalTitle: "Newest on OpenRouter",
-      liveLabel: "live",
-      ctaEyebrow: "How your assistant picks",
-      body: "Your assistant compares these against your task and live-tests the finalists."
-    }
+    toolList: [
+      { name: "list_facets", role: "vocabulary" },
+      { name: "find_models", role: "search & filter" },
+      { name: "get_models", role: "full specs" },
+      { name: "compare_models", role: "side-by-side diff" },
+      { name: "test_model", role: "live inference" }
+    ]
   },
   problem: {
     label: "Why this exists",
@@ -304,70 +306,77 @@ var SITE = {
     ]
   },
   caseStudy: {
-    label: "Case study",
+    label: "Real session",
     heading: "A real session, not a mockup",
-    subheading: "A Claude Code session picking a TypeScript code-review model. Real tool calls, real verdict.",
+    subheading: "Claude Sonnet 4.6 driven through the index9 MCP server, picking a model for a TypeScript code-review bot. Real prompt, real tool calls, real verdict.",
     prompt: {
       title: "The prompt",
-      body: "Pick a model for a TypeScript code-review bot that runs on every PR. I want quality without paying frontier rates on routine reviews. Test against this diff."
+      body: "Pick a model for a TypeScript code-review bot that runs on every PR. I want real quality without paying frontier rates. Quote model ids verbatim from the tool responses."
     },
     toolCalls: {
       title: "What the assistant did",
-      subtitle: "in order",
+      subtitle: "4 calls, 42s",
       calls: [
-        { tool: "find_models", params: "newest first", note: "skip stale training picks" },
         {
           tool: "find_models",
-          params: "code review + structured output",
+          params: "sortBy=created, function_calling + structured_output",
+          note: "skip stale training picks"
+        },
+        {
+          tool: "find_models",
+          params: "code review, maxPrice=$5/M, minContext=64K",
           note: "task fit"
         },
-        { tool: "find_models", params: "max $2/M, every-PR budget", note: "rule out frontier" },
-        { tool: "get_models", params: "8 candidates", note: "metadata lookup" },
         {
           tool: "compare_models",
-          params: "4 finalists, ~3000 token PR diff",
-          note: "per-PR cost projection"
+          params: "4 finalists, 3,000 prompt + 800 completion",
+          note: "per-PR cost diff"
         },
-        { tool: "test_model", params: "dry-run \xD7 4", note: "cost estimate" },
         {
           tool: "test_model",
-          params: "live \xD7 4, JSON output",
-          note: "real bug-catch test"
+          params: "dry-run \xD7 4, same token budget",
+          note: "cost confirmation"
         }
       ]
     },
-    consideredTitle: "Recent models, evaluated",
-    consideredSubtitle: "Candidates the assistant ruled in and out, with the reason.",
+    consideredTitle: "Candidates the session evaluated",
+    consideredSubtitle: "Lifted from the tool responses. Per-PR cost is the dry-run test_model output for a 3,000 token diff and an 800 token review.",
     consideredRows: [
       {
-        id: "openai/gpt-5.5",
-        age: "1d ago",
+        id: "anthropic/claude-opus-4.7-fast",
+        age: "5d ago",
         decision: "skip",
-        reason: "~$0.027 per PR, 5\xD7 the pick for the same outcome"
+        reason: "$30/M input, filtered out by the maxPrice constraint on the second find_models call"
+      },
+      {
+        id: "mistralai/devstral-medium",
+        age: "10mo ago",
+        decision: "tested",
+        reason: "$0.40/M input, completion-heavy at $2/M, $0.0028 per PR"
       },
       {
-        id: "xiaomi/mimo-v2.5-pro",
-        age: "3d ago",
+        id: "qwen/qwen3-coder",
+        age: "10mo ago",
         decision: "tested",
-        reason: "good structure, missed the precision edge case"
+        reason: "$0.22/M input, 1M context but no file_input, $0.0021 per PR"
       },
       {
-        id: "deepseek/deepseek-v4-flash",
-        age: "1d ago",
+        id: "google/gemini-3.1-flash-lite",
+        age: "1w ago",
         decision: "tested",
-        reason: "7\xD7 cheaper than the pick, but missed both bugs"
+        reason: "$0.25/M input, newest of the shortlist, adds reasoning and vision, $0.00195 per PR"
       },
       {
-        id: "z-ai/glm-5.1",
-        age: "2w ago",
+        id: "mistralai/codestral-2508",
+        age: "9mo ago",
         decision: "shortlisted",
-        reason: "caught both bugs at ~$0.005 per PR"
+        reason: "$0.30/M input, Mistral's coding-specific model, $0.00162 per PR"
       }
     ],
     verdict: {
       title: "The pick",
-      model: "z-ai/glm-5.1",
-      body: "Open-weight, $1.05 per million input tokens. Caught both bugs in the sample diff at roughly $0.005 per PR, about 5\xD7 cheaper than running gpt-5.5 on every commit."
+      model: "mistralai/codestral-2508",
+      body: "Lowest realistic per-PR cost at $0.00162 on a 3,000 token diff and an 800 token review. Mistral's coding-specific model, structured output, file input for diffs, 256K context. About 100\xD7 cheaper on input than running claude-opus-4.7-fast on every commit."
     }
   },
   toolsSection: {
@@ -832,6 +841,7 @@ var TestFailureReasonSchema = z6.enum([
 var TestDebugInfoSchema = z6.object({
   upstreamId: z6.string().optional(),
   providerName: z6.string().optional(),
+  modelPublisher: z6.string().optional(),
   finishReason: z6.string().optional(),
   upstreamError: z6.string().optional(),
   refusal: z6.string().optional(),
@@ -1211,8 +1221,8 @@ async function createServer() {
         sortOrder: z7.enum(["asc", "desc"]).optional().describe("Sort order. Defaults by sortBy."),
         createdAfter: z7.string().optional().describe("Lower bound for model created timestamp."),
         createdBefore: z7.string().optional().describe("Upper bound for model created timestamp."),
-        minPrice: z7.number().min(0).optional().describe("Minimum prompt price in USD per million tokens."),
-        maxPrice: z7.number().min(0).optional().describe("Maximum prompt price in USD per million tokens."),
+        minPrice: z7.number().min(0).optional().describe(PARAM_DESCRIPTIONS.minPrice),
+        maxPrice: z7.number().min(0).optional().describe(PARAM_DESCRIPTIONS.maxPrice),
         minContext: z7.number().int().min(1).optional().describe("Minimum context window in tokens."),
         capabilitiesAll: z7.array(z7.enum(CAPABILITIES)).optional().describe(PARAM_DESCRIPTIONS.capabilitiesAll),
         capabilitiesAny: z7.array(z7.enum(CAPABILITIES)).optional().describe(PARAM_DESCRIPTIONS.capabilitiesAny),

package/manifest.json

@@ -1,7 +1,7 @@
 {
   "manifest_version": "0.3",
   "name": "index9",
-  "version": "6.2.0",
+  "version": "6.4.0",
   "description": "Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor",
   "author": {
     "name": "Index9"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@index9/mcp",
-  "version": "6.3.0",
+  "version": "6.5.0",
   "license": "MIT",
   "repository": {
     "type": "git",
@@ -28,7 +28,7 @@
     "tsup": "^8.5.1",
     "typescript": "6.0.3",
     "vitest": "^4.1.6",
-    "@index9/core": "2.6.0"
+    "@index9/core": "2.8.0"
   },
   "engines": {
     "node": ">=20"