@tensorfeed/mcp-server 1.36.4 → 1.38.0

package/CHANGELOG.md

@@ -2,6 +2,30 @@
 
 All notable changes to the [TensorFeed.ai MCP server](https://github.com/RipperMercs/tensorfeed-mcp). Free tools work without configuration; premium tools require a bearer token via the `TENSORFEED_TOKEN` env var. Buy credits at [tensorfeed.ai/developers/agent-payments](https://tensorfeed.ai/developers/agent-payments).
 
+## 1.38.0 - 2026-06-03
+
+Description-only release. Sharpens the six foundational free tools (get_ai_news,
+get_ai_status, is_service_down, get_model_pricing, get_ai_today, premium_routing)
+so each states what it returns, why to call it instead of polling sources
+directly, and its tier. get_ai_today drops an inaccurate 24-hour-window claim
+(it returns the latest stories, not a strict time window). premium_routing now
+points at its signed sibling route_verdict. No tool, pricing, or behavior
+changes from 1.37.0.
+
+## 1.37.0 - 2026-06-02
+
+Adds four free agentic-web tools, bringing the catalog to 65 tools (41 free, 24
+premium):
+- `check_agent_ready`: score how agent-ready any tracked site is, 0 to 100, from
+  its x402 manifest, agent.json, OpenAPI spec, llms.txt, AI-bot crawlability,
+  and ai.txt.
+- `agent_ready_summary`: the cross-domain readiness picture across about 500
+  curated domains, with per-surface adoption shares and a top-10 leaderboard.
+- `check_crawler_access`: whether a site allows or blocks GPTBot, ClaudeBot, and
+  other AI crawlers, plus its llms.txt and ai.txt signals.
+- `crawler_access_summary`: the aggregate AI-crawler access map across the
+  tracked domain set.
+
 ## 1.36.4 - 2026-05-31
 
 Docs-only release. The README now opens with the Route Verdict quickstart: a

package/dist/index.js

@@ -178,7 +178,7 @@ server.registerResource('latest_news', 'tensorfeed://news/latest', {
     };
 });
 // ── Tool: get_ai_news ───────────────────────────────────────────────
-registerTool('get_ai_news', 'Get the latest AI news articles from TensorFeed.ai. Aggregates from 15+ sources including Anthropic, OpenAI, Google, TechCrunch, The Verge, arXiv, and more.', {
+registerTool('get_ai_news', 'Get the latest AI news from TensorFeed.ai as a ranked list with title, source, URL, snippet, and publish time, filterable by category (e.g. "anthropic", "openai", "research", "tools"). Aggregates 15+ sources (Anthropic, OpenAI, Google, TechCrunch, The Verge, arXiv, and more) into one normalized feed, so an agent reads one schema instead of polling each outlet. Free, no auth.', {
     category: z.string().optional().describe('Filter by category (e.g. "anthropic", "openai", "research", "tools")'),
     limit: z.number().min(1).max(50).optional().describe('Number of articles to return (default 10, max 50)'),
 }, async ({ category, limit }) => {
@@ -193,7 +193,7 @@ registerTool('get_ai_news', 'Get the latest AI news articles from TensorFeed.ai.
     return { content: [{ type: 'text', text: text || 'No articles found.' }] };
 });
 // ── Tool: get_ai_status ─────────────────────────────────────────────
-registerTool('get_ai_status', 'Get real-time operational status of major AI services (Claude, OpenAI, Gemini, Mistral, Cohere, Replicate, Hugging Face).', {}, async () => {
+registerTool('get_ai_status', 'Get the real-time operational status of major AI services (Claude, OpenAI, Gemini, Mistral, Cohere, Replicate, Hugging Face), including per-component breakdowns and an operational/degraded/down rollup per provider. One cross-provider status call instead of checking each vendor\'s status page, useful before an agent routes a request to a model that may be impaired. Free, no auth.', {}, async () => {
     const data = await fetchJSON('/status');
     const text = data.services
         .map(s => {
@@ -206,7 +206,7 @@ registerTool('get_ai_status', 'Get real-time operational status of major AI serv
     return { content: [{ type: 'text', text: `AI Service Status:\n${text}` }] };
 });
 // ── Tool: is_service_down ───────────────────────────────────────────
-registerTool('is_service_down', 'Check if a specific AI service is currently down or experiencing issues.', {
+registerTool('is_service_down', 'Check whether one named AI service (e.g. "claude", "openai", "gemini", "mistral", "cohere", "hugging face", "replicate") is currently operational, degraded, or down, with its component-level breakdown. Matches on service or provider name and lists available services if there is no match, so an agent can gate a call on live status before sending traffic. Free, no auth.', {
     service: z.string().describe('Service name to check (e.g. "claude", "openai", "gemini", "mistral", "cohere", "hugging face", "replicate")'),
 }, async ({ service }) => {
     const data = await fetchJSON('/status');
@@ -226,8 +226,63 @@ registerTool('is_service_down', 'Check if a specific AI service is currently dow
             }]
     };
 });
+// Tool: check_agent_ready
+registerTool('check_agent_ready', 'Score how agent-ready a website is, 0 to 100, from its public surfaces: x402 payment manifest, /.well-known/agent.json, an OpenAPI spec, llms.txt, AI-bot crawlability, and ai.txt. Returns the score, the tier (closed, emerging, ready, or advanced), and exactly which surfaces the site exposes. Unlike single-site "is my site agent-ready" scanners, this reads from TensorFeed\'s daily-crawled cross-domain dataset, so the same call works for any tracked domain and the scoring rule is published and identical for every site. Free, no auth.', {
+    domain: z.string().describe('Bare domain to score, e.g. "stripe.com" (no scheme, no path)'),
+}, async ({ domain }) => {
+    const data = await fetchJSON(`/agent-ready/site?domain=${encodeURIComponent(domain)}`);
+    if (!data.found || !data.readiness) {
+        return { content: [{ type: 'text', text: `${data.domain} is not in TensorFeed's tracked set yet (no agent-readiness score). About 500 curated domains are tracked.` }] };
+    }
+    const r = data.readiness;
+    const present = Object.entries(r.surfaces).filter(([, v]) => v).map(([k]) => k);
+    const text = `${data.domain}: agent-readiness ${r.score}/100 (${r.tier})\n` +
+        `Surfaces present: ${present.length ? present.join(', ') : 'none'}\n` +
+        `x402=${r.surfaces.x402} agent.json=${r.surfaces.agentJson} openapi=${r.surfaces.openapi} llms.txt=${r.surfaces.llmsTxt} crawlable=${r.surfaces.crawlable} ai.txt=${r.surfaces.aiTxt}\n` +
+        `Last checked: ${data.captured_at ?? 'n/a'}`;
+    return { content: [{ type: 'text', text }] };
+});
+// Tool: agent_ready_summary
+registerTool('agent_ready_summary', 'Get the state of the agentic web. Across about 500 curated domains, returns the share exposing each agent surface (x402, agent.json, OpenAPI, llms.txt, crawlable, ai.txt), the readiness-tier distribution, and a top-10 leaderboard of the most agent-ready sites. This aggregate, cross-domain view is exactly what a single-site scanner cannot give you. Free, no auth.', {}, async () => {
+    const d = await fetchJSON('/agent-ready/summary.json');
+    const a = d.adoption_pct;
+    const lb = (d.leaderboard || []).slice(0, 10).map((e, i) => `${i + 1}. ${e.domain} (${e.score}, ${e.tier})`).join('\n');
+    const text = `Agentic web readiness, ${d.profiled}/${d.domains_tracked} domains profiled (captured ${d.captured_at ?? 'n/a'}):\n` +
+        `Surface adoption: x402 ${a.x402}%, agent.json ${a.agentJson}%, openapi ${a.openapi}%, llms.txt ${a.llmsTxt}%, crawlable ${a.crawlable}%, ai.txt ${a.aiTxt}%\n` +
+        `Tiers: ${Object.entries(d.tier_distribution || {}).map(([t, n]) => `${t} ${n}`).join(', ')}\n` +
+        `Most agent-ready:\n${lb}`;
+    return { content: [{ type: 'text', text }] };
+});
+// Tool: check_crawler_access
+registerTool('check_crawler_access', 'Check which AI bots a website allows or blocks in its robots.txt: GPTBot, ClaudeBot, PerplexityBot, CCBot, Google-Extended, Bytespider, and more, with a per-bot verdict (allowed, blocked, partial, or unknown), plus whether the site publishes llms.txt and ai.txt. Reports the site\'s stated policy, not enforcement (robots.txt compliance is voluntary). Free, no auth.', {
+    domain: z.string().describe('Bare domain to check, e.g. "nytimes.com" (no scheme, no path)'),
+}, async ({ domain }) => {
+    const data = await fetchJSON(`/ai-crawler-access/site?domain=${encodeURIComponent(domain)}`);
+    if (!data.found || !data.record) {
+        return { content: [{ type: 'text', text: `${data.domain} is not in TensorFeed's tracked set yet. About 500 curated domains are tracked for AI-crawler access.` }] };
+    }
+    const rec = data.record;
+    const bots = Object.entries(rec.bots).map(([b, v]) => `  ${b}: ${v}`).join('\n');
+    const text = `${data.domain} (robots.txt HTTP ${rec.robotsStatus ?? 'n/a'}) AI-bot access:\n${bots}\n` +
+        `llms.txt: ${rec.hasLlmsTxt ? 'yes' : 'no'}, ai.txt: ${rec.hasAiTxt ? 'yes' : 'no'}\n` +
+        `Stated policy only; compliance is voluntary. Last checked: ${data.captured_at ?? 'n/a'}`;
+    return { content: [{ type: 'text', text }] };
+});
+// Tool: crawler_access_summary
+registerTool('crawler_access_summary', 'Get the aggregate AI-crawler access map across about 500 curated domains: the percentage of sites that block each AI bot (the publisher-versus-AI-crawler picture), plus llms.txt and ai.txt adoption rates. Unlike a single-site robots.txt checker, this is the cross-domain trend view of who is shutting AI crawlers out. Free, no auth.', {}, async () => {
+    const d = await fetchJSON('/ai-crawler-access/summary.json');
+    const blocked = Object.entries(d.bot_blocked_pct || {})
+        .sort((x, y) => y[1] - x[1])
+        .slice(0, 8)
+        .map(([b, p]) => `  ${b}: ${p}% blocked`)
+        .join('\n');
+    const text = `AI-crawler access across ${d.domains_with_data}/${d.domains_tracked} tracked domains (captured ${d.captured_at ?? 'n/a'}):\n` +
+        `Most-blocked AI bots:\n${blocked}\n` +
+        `llms.txt adoption: ${d.llms_txt_adoption_pct}%, ai.txt adoption: ${d.ai_txt_adoption_pct}%`;
+    return { content: [{ type: 'text', text }] };
+});
 // ── Tool: get_model_pricing ─────────────────────────────────────────
-registerTool('get_model_pricing', 'Get AI model pricing comparison across all major providers (Anthropic, OpenAI, Google, Meta, Mistral, Cohere). Prices per 1M tokens.', {}, async () => {
+registerTool('get_model_pricing', 'Get AI model pricing across major providers (Anthropic, OpenAI, Google, Meta, Mistral, Cohere) in one normalized table: input and output price per 1M tokens, context window, and release date per model. One cross-provider comparison instead of scraping six pricing pages, so an agent can pick the cheapest model that fits its context and budget. Free, no auth.', {}, async () => {
     const data = await fetchJSON('/models');
     const text = data.providers
         .map(p => {
@@ -307,7 +362,7 @@ registerTool('get_model_deprecations', "Get the AI model deprecation calendar. P
     return { content: [{ type: 'text', text: header + sections }] };
 });
 // ── Tool: get_ai_today ──────────────────────────────────────────────
-registerTool('get_ai_today', 'Get a summary of what happened in AI today. Returns the top stories from the last 24 hours.', {
+registerTool('get_ai_today', 'Get a quick digest of the top AI stories from the latest TensorFeed news feed, each with title, source, and URL. A shorter, headline-only companion to get_ai_news for when an agent just needs a fast read on what is happening in AI right now rather than the full article set. Free, no auth.', {
     limit: z.number().min(1).max(20).optional().describe('Number of stories (default 5)'),
 }, async ({ limit }) => {
     const data = await fetchJSON(`/news?limit=${limit || 5}`);
@@ -557,7 +612,7 @@ registerTool('get_account_usage', 'Show per-endpoint usage for the configured Te
     };
 });
 // ── Tool: premium_routing (1 credit) ────────────────────────────────
-registerTool('premium_routing', 'Get a ranked list of recommended AI models for a task with full score breakdown (quality, availability, cost, latency). Costs 1 credit ($0.02).', {
+registerTool('premium_routing', 'Get a ranked list of recommended AI models for a task (code, reasoning, creative, or general), each with a composite score plus the quality, availability, cost, and latency components that produced it, and the per-model input/output pricing. Constrain with budget, min_quality, and top_n so the ranking reflects your actual limits instead of a generic leaderboard. Costs 1 credit ($0.02), billed against your TENSORFEED_TOKEN. For a single signed routing decision with reasoning, see route_verdict.', {
     task: z.enum(['code', 'reasoning', 'creative', 'general']).optional().describe('Task type the model needs to be good at (default: general)'),
     budget: z.number().optional().describe('Max blended USD per 1M tokens'),
     min_quality: z.number().min(0).max(1).optional().describe('Minimum quality score in [0, 1]'),

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tensorfeed/mcp-server",
-  "version": "1.36.4",
+  "version": "1.38.0",
   "mcpName": "ai.tensorfeed/mcp-server",
   "description": "MCP server for TensorFeed.ai - AI news, status, model data, and premium endpoints (routing, cost projection, forecast, history series, news search, webhook watches with digest tier, enriched directory) for AI agents",
   "main": "dist/index.js",

package/server.json

@@ -3,7 +3,7 @@
   "name": "ai.tensorfeed/mcp-server",
   "title": "TensorFeed",
   "description": "AI news, model pricing, service status, and machine-payable premium tools. AFTA-certified.",
-  "version": "1.36.4",
+  "version": "1.38.0",
   "websiteUrl": "https://tensorfeed.ai/developers/agent-payments",
   "repository": {
     "url": "https://github.com/RipperMercs/tensorfeed-mcp",
@@ -20,7 +20,7 @@
       "registryType": "npm",
       "registryBaseUrl": "https://registry.npmjs.org",
       "identifier": "@tensorfeed/mcp-server",
-      "version": "1.36.4",
+      "version": "1.38.0",
       "runtimeHint": "npx",
       "transport": {
         "type": "stdio"
@@ -54,6 +54,10 @@
         "get_honeypot_iocs",
         "check_afta_certification",
         "get_agent_reputation_card",
+        "check_agent_ready",
+        "agent_ready_summary",
+        "check_crawler_access",
+        "crawler_access_summary",
         "mcp_registry_snapshot",
         "probe_latest",
         "get_ai_papers_trending",