@index9/mcp 5.3.0 → 6.0.0

package/dist/cli.js

@@ -235,184 +235,167 @@ var SITE = {
   },
   hero: {
     titleLine1: "Pick the right AI model",
-    titleLine2: "without leaving your editor",
-    subtitle: "Index9 is an MCP server. Your AI assistant searches, compares, and live-tests 300+ models on your prompt, so picks are measured, not guessed.",
-    proof: ["Live OpenRouter data", "300+ models, refreshed every 30 min"],
+    titleLine2: "from chat",
+    subtitle: "Index9 is an MCP server. Your coding assistant uses it to search, compare, and live-test 300+ models on the task you're working on, so it recommends the best fit.",
+    proof: ["Live OpenRouter data \xB7 300+ models \xB7 refreshed every 30 min"],
     pricingNote: "Free. You only pay OpenRouter for live model calls.",
     getStarted: "Add index9 to your editor",
     seeHowItWorks: "See a real session",
     updatedBadge: "OpenRouter data \xB7 refreshed "
   },
+  problem: {
+    label: "Why this exists",
+    heading: "Your assistant's model knowledge is stale",
+    body: [
+      'New models ship every week. Pricing changes. "Use GPT-4" or "use Claude 3.5" is usually months behind reality.',
+      "Without live data, your assistant defaults to whatever it learned in training \u2014 often a model that's been superseded by something cheaper or better-suited to your task.",
+      "Index9 gives it the data and the tools to actually compare."
+    ]
+  },
   howItWorks: {
     label: "How it works",
-    heading: "Your assistant does the model-picking. You stay in the chat.",
-    subtitle: "Index9 adds five MCP tools to your editor. When you ask about models, your assistant calls them, and gets live data back.",
+    heading: "How it works",
+    subtitle: "Index9 adds 5 tools to your editor. Your assistant calls them when you ask about models.",
     steps: [
       {
         number: "1",
-        title: "You ask your assistant",
-        body: '"Pick the cheapest model that can summarize this document well." Just chat. No new UI to learn.'
+        title: "You ask in chat",
+        body: '"Pick the cheapest model that can review TypeScript PRs well."'
       },
       {
         number: "2",
         title: "Your assistant calls index9",
-        body: "It pulls live OpenRouter data: search results, full specs, cost diffs, and test outputs on your prompt."
+        body: "It searches live model data, compares finalists, and runs your prompt against the top candidates."
       },
       {
         number: "3",
-        title: "You get a measured recommendation",
-        body: "The assistant compares actual outputs and recommends the model that fits your constraints. Evidence, not guesswork."
+        title: "You get a measured pick",
+        body: "Backed by real cost numbers and real outputs \u2014 not training-data memory."
       }
     ]
   },
   caseStudy: {
     label: "Case study",
-    heading: "A real session, not a mock",
-    subheading: "A Claude Code session picking a TypeScript code-review model. Actual tool calls, decisions, and final pick. Captured 2026-04-24.",
+    heading: "A real session, not a mockup",
+    subheading: "A Claude Code session picking a TypeScript code-review model. Real tool calls, real verdict.",
     prompt: {
       title: "The prompt",
-      body: "Pick 3 models for a TypeScript code-review bot. Test them on a sample PR diff and recommend the best one. Quality matters more than price."
+      body: "Pick a model for a TypeScript code-review bot that runs on every PR. I want real quality without paying frontier rates on routine reviews. Test against this sample diff."
     },
     toolCalls: {
-      title: "Selection path",
+      title: "What the assistant did",
       subtitle: "in order",
       calls: [
+        { tool: "find_models", params: "newest first", note: "skip stale training picks" },
         {
           tool: "find_models",
-          params: "sortBy=created, limit=10",
-          note: "recent releases"
-        },
-        {
-          tool: "find_models",
-          params: 'q="code review reasoning", structured_output',
+          params: "code review + structured output",
           note: "task fit"
         },
-        {
-          tool: "find_models",
-          params: 'q="not frontier price", maxPrice=6',
-          note: "budget filter"
-        },
-        { tool: "get_models", params: "\xD7 12 candidates", note: "metadata lookup" },
+        { 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: "ids=[3 finalists], expectedPromptTokens=6000",
-          note: "workload-cost flip"
+          params: "4 finalists, ~3000 token PR diff",
+          note: "per-PR cost projection"
         },
-        { tool: "test_model", params: "dryRun \xD7 2", note: "cost estimate" },
+        { tool: "test_model", params: "dry-run \xD7 4", note: "cost estimate" },
         {
           tool: "test_model",
-          params: "live \xD7 2, enforceJson=true",
-          note: "real inference"
+          params: "live \xD7 4, JSON output",
+          note: "real bug-catch test"
         }
       ]
     },
-    consideredTitle: "Every recent model, evaluated",
-    consideredSubtitle: "Recent releases were checked with explicit accept, test, or skip decisions.",
+    consideredTitle: "Recent models, evaluated",
+    consideredSubtitle: "A trimmed view of the candidates the assistant ruled in and out. Each row pairs a decision with the reason behind it.",
     consideredRows: [
-      {
-        id: "openai/gpt-5.5-pro",
-        age: "6h ago",
-        decision: "skip",
-        reason: "too expensive for every PR"
-      },
       {
         id: "openai/gpt-5.5",
-        age: "6h ago",
+        age: "1d ago",
         decision: "skip",
-        reason: "frontier-priced vs Codex"
+        reason: "~$0.027 per PR, 5\xD7 the pick for the same outcome"
       },
       {
-        id: "deepseek/deepseek-v4-pro",
-        age: "14h ago",
+        id: "xiaomi/mimo-v2.5-pro",
+        age: "3d ago",
         decision: "tested",
-        reason: "live test hit upstream 429 twice"
+        reason: "good structure, missed the precision edge case"
       },
       {
         id: "deepseek/deepseek-v4-flash",
-        age: "14h ago",
-        decision: "skip",
-        reason: "cheaper sibling, lower quality expected"
-      },
-      {
-        id: "xiaomi/mimo-v2.5-pro",
-        age: "2d ago",
-        decision: "shortlisted",
-        reason: "recent + reasoning + structured output"
-      },
-      {
-        id: "inclusionai/ling-2.6-1t:free",
         age: "1d ago",
-        decision: "skip",
-        reason: "no reasoning capability flag"
+        decision: "tested",
+        reason: "7\xD7 cheaper than the pick, but missed both bugs"
       },
       {
-        id: "arcee-ai/trinity-large-thinking",
-        age: "3w ago",
-        decision: "skip",
-        reason: "MiMo Pro had stronger positioning"
+        id: "z-ai/glm-5.1",
+        age: "2w ago",
+        decision: "shortlisted",
+        reason: "caught both bugs at ~$0.005 per PR"
       }
     ],
     verdict: {
-      title: "The final pick",
-      model: "openai/gpt-5.3-codex",
-      body: "The only tested model that caught both sample bugs. About $0.015 per PR: higher than budget models, far below frontier rates."
+      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."
     },
     quote: {
-      body: "The cheapest candidate ran 4\xD7 cheaper than Codex, and missed both bugs in the sample diff. The only way to know was a live test.",
-      attribution: "index9 session trace, 2026-04-24"
+      body: "The frontier model would have caught both bugs, at 5\xD7 the cost. The cheapest candidate missed them entirely. Only the live test surfaced the model that did both.",
+      attribution: "index9 session trace"
     }
   },
   toolsSection: {
     label: "Tools",
-    heading: "Five MCP tools, composable in any client",
-    subheading: "Discover, shortlist, compare, cost-model, and live-test. Your assistant chains them together to make a measured pick.",
-    openRouterKey: "OpenRouter API key (live tests only)",
-    noKeyRequired: "No API key required",
+    heading: "The 5 tools",
+    subheading: "Your assistant chains these together. You don't call them directly.",
+    openRouterKey: "OpenRouter API key",
+    noKeyRequired: "No key required",
     requiresLabel: "Requires ",
     cards: [
       {
         name: "list_facets",
-        action: "Discover",
+        action: "list_facets",
         displayName: "list_facets",
         fullName: null,
-        description: "List the live filter vocabulary (providers, capabilities, modalities) before constructing a search.",
+        description: "Lists available providers, capabilities, and modalities to filter by.",
         badge: null,
         requiresKey: false
       },
       {
         name: "find_models",
-        action: "Shortlist",
+        action: "find_models",
         displayName: "find_models",
         fullName: null,
-        description: `Filter ${MODEL_COUNT} models by price, context, and capabilities. Natural-language search refines the ranking.`,
+        description: `Searches ${MODEL_COUNT} models by price, context size, capabilities, or natural language.`,
         badge: null,
         requiresKey: false
       },
       {
         name: "get_models",
-        action: "Inspect",
+        action: "get_models",
         displayName: "get_models",
         fullName: null,
-        description: "Inspect current pricing, limits, and capabilities for any model.",
+        description: "Pulls full specs and current pricing for any model.",
         badge: null,
         requiresKey: false
       },
       {
         name: "compare_models",
-        action: "Compare",
+        action: "compare_models",
         displayName: "compare_models",
         fullName: null,
-        description: "Side-by-side spec, capability, and workload-cost diff for 2\u201310 finalists.",
+        description: "Diffs 2\u201310 finalists side-by-side. Flags the cheapest pick for your expected token mix.",
         badge: null,
         requiresKey: false
       },
       {
         name: "test_model",
-        action: "Run live tests",
+        action: "test_model",
         displayName: "test_model",
         fullName: null,
-        description: "Run one prompt across models and compare output, latency, and cost.",
-        badge: "Live Testing",
+        description: "Runs your prompt across models. Returns output, latency, and real cost. Or dry-run for cost only.",
+        badge: "Live",
         requiresKey: true
       }
     ]
@@ -423,7 +406,7 @@ var SITE = {
     items: [
       {
         question: "What is MCP?",
-        answer: "MCP (Model Context Protocol) lets AI assistants call external tools. index9 adds five composable tools (list_facets, find_models, get_models, compare_models, test_model) to any MCP-compatible client.",
+        answer: "A protocol that lets AI assistants call external tools. Index9 is one of those tools.",
         link: {
           label: "Learn more about MCP",
           url: "https://modelcontextprotocol.io"
@@ -431,45 +414,40 @@ var SITE = {
       },
       {
         question: "Who is index9 for?",
-        answer: "Developers using AI coding assistants (Claude Code, Cursor, Codex, VS Code) who want their assistant to pick models based on live cost and quality data, not training-data guesses.",
+        answer: "Developers using Claude Code, Cursor, VS Code, or Codex who want their assistant to pick models from current data instead of training-data memory.",
         link: null
       },
       {
-        question: "How does live testing work?",
-        answer: `test_model sends your prompt to 1\u2013${LIMITS.testModelsMax} models via OpenRouter and returns output, latency, token usage, and cost. Live tests require an OpenRouter key; dryRun=true only estimates cost (pass expectedPromptTokens to model larger workloads without pasting filler).`,
+        question: "Does it pick the model for me?",
+        answer: "No \u2014 it gives your assistant the data (search results, specs, cost diffs, live test outputs). Your assistant makes the call.",
         link: null
       },
       {
-        question: "Does index9 recommend which model to use?",
-        answer: "index9 returns outputs, latency, cost, and specs. Your assistant uses those results to make the recommendation.",
+        question: "How does live testing work?",
+        answer: `test_model sends your prompt to up to ${LIMITS.testModelsMax} models via OpenRouter and returns output, latency, tokens, and cost. Dry-run mode estimates cost without running inference.`,
         link: null
       },
       {
-        question: "How is compare_models different from calling get_models on each candidate?",
-        answer: "compare_models returns a diff matrix (which fields are equal, which differ), plus convenience picks: cheapestForPromptPerMillion, largestContext, and (when you pass expectedPromptTokens + expectedCompletionTokens) cheapestForRealisticWorkload accounting for prompt:completion ratio differences. One call instead of N parallel get_models calls plus manual diffing.",
+        question: "Which models?",
+        answer: `${MODEL_COUNT} from OpenRouter \u2014 OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, and more. Metadata refreshes every 30 minutes.`,
         link: null
       },
       {
-        question: "What models are available?",
-        answer: `index9 covers ${MODEL_COUNT} OpenRouter models, including OpenAI, Anthropic, Google, Meta, Mistral, and others. Metadata refreshes every 30 minutes.`,
+        question: "Do you store my prompts or keys?",
+        answer: "No. Index9 doesn't store prompts, outputs, or API keys. Live tests are proxied straight to OpenRouter.",
         link: null
       },
       {
         question: "What's the project status?",
-        answer: "The hosted API and MCP server are stable and in active use. Issues and feature requests welcome on GitHub.",
-        link: null
-      },
-      {
-        question: "Is my data stored?",
-        answer: "No. index9 does not store prompts, outputs, or API keys. Live tests are proxied to OpenRouter.",
+        answer: "Stable and in active use. Issues and feature requests welcome on GitHub.",
         link: null
       }
     ]
   },
   install: {
     label: "Setup",
-    heading: "Add index9 to your editor",
-    subheading: "Choose your client and copy the config.",
+    heading: "Install",
+    subheading: "Pick your editor and paste the config.",
     configs: [
       {
         id: "cursor",
@@ -501,14 +479,14 @@ var SITE = {
       {
         id: "claude-code",
         label: "Claude Code",
-        paths: ["Terminal command"],
+        paths: [],
         config: `claude mcp add --transport stdio index9 -- npx -y @index9/mcp@latest`,
         copyHint: "# Run in terminal (adds to ~/.claude.json)"
       },
       {
         id: "codex",
         label: "Codex",
-        paths: ["Terminal command"],
+        paths: [],
         config: `codex mcp add index9 -- npx -y @index9/mcp@latest`,
         copyHint: "# Run in terminal (adds to ~/.codex/config.toml)"
       }
@@ -516,8 +494,9 @@ var SITE = {
     copyButton: "Copy",
     copiedButton: "Copied",
     copyAriaLabel: "Copy configuration",
-    setupNote: "Need live tests or custom setup?",
-    setupLink: "Set up live testing",
+    copiedAnnouncement: "Configuration copied to clipboard",
+    setupNote: "Want live tests?",
+    setupLink: "Add an OpenRouter key",
     setupUrl: "https://github.com/index9-org/mcp#openrouter-api-key"
   },
   footer: {

package/manifest.json

@@ -1,7 +1,7 @@
 {
   "manifest_version": "0.3",
   "name": "index9",
-  "version": "5.2.0",
+  "version": "5.3.0",
   "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": "5.3.0",
+  "version": "6.0.0",
   "license": "MIT",
   "repository": {
     "type": "git",
@@ -21,10 +21,10 @@
   },
   "dependencies": {
     "@modelcontextprotocol/sdk": "^1.29.0",
-    "zod": "^4.3.6"
+    "zod": "^4.4.3"
   },
   "devDependencies": {
-    "@types/node": "^25.6.0",
+    "@types/node": "^25.6.1",
     "tsup": "^8.5.1",
     "typescript": "6.0.3",
     "vitest": "^4.1.5",