@tensorfeed/mcp-server 1.36.1 → 1.36.2

package/CHANGELOG.md

@@ -2,6 +2,21 @@
 
 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).
 
+## 1.36.2 - 2026-05-31
+
+Pricing-copy and catalog-accuracy corrections. No change to the free/paid
+split or the actual on-chain charge.
+
+- Corrected the stated credit cost on `pricing_series`, `benchmark_series`,
+  and `status_uptime` and their free-sibling pointers back to 1 credit
+  ($0.02). These are Tier 2, which maps to 1 credit in TIER_COSTS; release
+  1.36.1 had wrongly relabeled them 2 credits.
+- Catalog accuracy: `server.json` now lists the true 59 tools (36 free,
+  23 premium), adding 5 free tools that were omitted (`get_model_deprecations`,
+  `get_ai_supply_chain_iocs`, `get_honeypot_iocs`, `check_afta_certification`,
+  `get_agent_reputation_card`) and removing the phantom `mcp_registry_series`;
+  the manifest long_description now reads 59 tools.
+
 ## 1.36.1 - 2026-05-31
 
 Security hardening only. No API changes; agents see the same tools.
@@ -14,8 +29,6 @@ Security hardening only. No API changes; agents see the same tools.
   cannot overflow the agent's context window.
 - Path parameters (watch id, company ticker) are now URL-encoded and
   schema-validated before they reach a request path.
-- Reconciled the stated credit cost on the free pricing, benchmark, and
-  status series pointers (they correctly read 2 credits now).
 
 ## 1.36.0 - 2026-05-28
 
@@ -74,14 +87,14 @@ Premium endpoint audit (2026-05-14) through the lens "does this clearly save the
 ### Changed (pricing)
 Six tools mapping to strict-premium TF Worker endpoints are repriced from Tier 1 ($0.02) into higher tiers reflecting the curated-derived-metrics value they provide. Tool descriptions updated to advertise the new prices:
 
-- `pricing_series`: 1 credit ($0.02) -> 2 credits ($0.04)
-- `benchmark_series`: 1 credit ($0.02) -> 2 credits ($0.04)
-- `status_uptime`: 1 credit ($0.02) -> 2 credits ($0.04)
-- `status_leaderboard`: 1 credit ($0.02) -> 3 credits ($0.06)
-- `provider_deepdive`: 1 credit ($0.02) -> 3 credits ($0.06)
-- `probe_series_premium`: 1 credit ($0.02) -> 3 credits ($0.06)
+- `pricing_series`: Tier 2, 1 credit ($0.02)
+- `benchmark_series`: Tier 2, 1 credit ($0.02)
+- `status_uptime`: Tier 2, 1 credit ($0.02)
+- `status_leaderboard`: Tier 3, 5 credits ($0.10)
+- `provider_deepdive`: Tier 3, 5 credits ($0.10)
+- `probe_series_premium`: Tier 3, 5 credits ($0.10)
 
-Tier 2 ($0.04) tools are single-entity full-window historical lookups. Tier 3 ($0.06) tools are heavy multi-source aggregations and TF-unique measurements.
+Tier 2 (1 credit, $0.02) tools are single-entity full-window historical lookups. Tier 3 (5 credits, $0.10) tools are heavy multi-source aggregations and TF-unique measurements.
 
 Rationale: per the 70/30 premium-lock framework, strict-premium endpoints carry TF's actual moat. The Tier 1 ($0.02) baseline price made sense during the demand-discovery temp-unlock; now that these endpoints are gated as strict-premium (v1.30.0) and the gate is observable, repricing into Tier 2/3 sets prices closer to the curated-derived-metrics market (Glassnode / Kaito comparables). Per-call USD cost is now legible alongside credit count in every affected tool description.
 

package/dist/index.js

@@ -585,7 +585,7 @@ registerTool('premium_routing', 'Get a ranked list of recommended AI models for
     return { content: [{ type: 'text', text: `Routing for "${data.task}":\n\n${list}${billing}` }] };
 });
 // ── Tool: pricing_series_free (free, 7-day cap) ─────────────────────
-registerTool('pricing_series_free', 'Daily price points for one AI model over the last 1 to 7 days, free. For windows up to 90 days use pricing_series (2 credits).', {
+registerTool('pricing_series_free', 'Daily price points for one AI model over the last 1 to 7 days, free. For windows up to 90 days use pricing_series (1 credit).', {
     model: z.string().describe('Model id or display name (e.g. "Claude Opus 4.7" or "claude-opus-4-7")'),
     days: z.number().min(1).max(7).optional().describe('Rolling window length 1 to 7 days (default 7)'),
 }, async ({ model, days }) => {
@@ -601,13 +601,13 @@ registerTool('pricing_series_free', 'Daily price points for one AI model over th
         content: [
             {
                 type: 'text',
-                text: `${data.model} (${data.provider ?? 'unknown'}) ${data.points.length} points over ${data.points.length} days\n${summary}\nFor up to 90 days, use the pricing_series tool (2 credits).`,
+                text: `${data.model} (${data.provider ?? 'unknown'}) ${data.points.length} points over ${data.points.length} days\n${summary}\nFor up to 90 days, use the pricing_series tool (1 credit).`,
             },
         ],
     };
 });
 // ── Tool: benchmark_series_free (free, 7-day cap) ───────────────────
-registerTool('benchmark_series_free', 'Daily benchmark scores for one model+benchmark over the last 1 to 7 days, free. Benchmark keys: swe_bench, mmlu_pro, gpqa_diamond, math, human_eval. For windows up to 90 days use benchmark_series (2 credits).', {
+registerTool('benchmark_series_free', 'Daily benchmark scores for one model+benchmark over the last 1 to 7 days, free. Benchmark keys: swe_bench, mmlu_pro, gpqa_diamond, math, human_eval. For windows up to 90 days use benchmark_series (1 credit).', {
     model: z.string().describe('Model id or display name'),
     benchmark: z.string().describe('Benchmark key'),
     days: z.number().min(1).max(7).optional().describe('Rolling window length 1 to 7 days (default 7)'),
@@ -630,7 +630,7 @@ registerTool('benchmark_series_free', 'Daily benchmark scores for one model+benc
     };
 });
 // ── Tool: status_uptime_free (free, 7-day cap) ──────────────────────
-registerTool('status_uptime_free', 'Daily uptime rollup for one provider over the last 1 to 7 days, free. For windows up to 90 days use status_uptime (2 credits).', {
+registerTool('status_uptime_free', 'Daily uptime rollup for one provider over the last 1 to 7 days, free. For windows up to 90 days use status_uptime (1 credit).', {
     provider: z.string().describe('Provider name (e.g. anthropic, openai, google)'),
     days: z.number().min(1).max(7).optional().describe('Rolling window length 1 to 7 days (default 7)'),
 }, async ({ provider, days }) => {
@@ -673,8 +673,8 @@ registerTool('status_leaderboard_free', 'Cross-provider uptime leaderboard, rank
         ],
     };
 });
-// ── Tool: pricing_series (2 credits) ────────────────────────────────
-registerTool('pricing_series', 'Daily price points for one AI model with min/max/delta summary. Default range = last 30 days, max 90 days. Costs 2 credits ($0.04). Strict premium, no free trial; the 7-day-capped sibling pricing_series_free is the discovery option.', {
+// ── Tool: pricing_series (1 credit) ─────────────────────────────────
+registerTool('pricing_series', 'Daily price points for one AI model with min/max/delta summary. Default range = last 30 days, max 90 days. Costs 1 credit ($0.02). Strict premium, no free trial; the 7-day-capped sibling pricing_series_free is the discovery option.', {
     model: z.string().describe('Model id or display name (e.g. "Claude Opus 4.7" or "claude-opus-4-7")'),
     from: z.string().optional().describe('Start date YYYY-MM-DD UTC (default: 30 days ago)'),
     to: z.string().optional().describe('End date YYYY-MM-DD UTC (default: today)'),
@@ -698,8 +698,8 @@ registerTool('pricing_series', 'Daily price points for one AI model with min/max
         ],
     };
 });
-// ── Tool: benchmark_series (2 credits) ──────────────────────────────
-registerTool('benchmark_series', 'Score evolution for a single benchmark on one AI model. Costs 2 credits ($0.04). Strict premium, no free trial; the 7-day-capped sibling benchmark_series_free is the discovery option. Benchmark keys: swe_bench, mmlu_pro, gpqa_diamond, math, human_eval.', {
+// ── Tool: benchmark_series (1 credit) ───────────────────────────────
+registerTool('benchmark_series', 'Score evolution for a single benchmark on one AI model. Costs 1 credit ($0.02). Strict premium, no free trial; the 7-day-capped sibling benchmark_series_free is the discovery option. Benchmark keys: swe_bench, mmlu_pro, gpqa_diamond, math, human_eval.', {
     model: z.string().describe('Model id or display name'),
     benchmark: z.string().describe('Benchmark key (e.g. swe_bench, mmlu_pro, gpqa_diamond, math, human_eval)'),
     from: z.string().optional().describe('Start date YYYY-MM-DD UTC (default: 30 days ago)'),
@@ -724,8 +724,8 @@ registerTool('benchmark_series', 'Score evolution for a single benchmark on one
         ],
     };
 });
-// ── Tool: status_uptime (2 credits) ─────────────────────────────────
-registerTool('status_uptime', 'Daily uptime rollup for one provider with operational/degraded/down day counts and uptime % (degraded counts as half-credit). Costs 2 credits ($0.04). Strict premium, no free trial; the 7-day-capped sibling status_uptime_free is the discovery option.', {
+// ── Tool: status_uptime (1 credit) ──────────────────────────────────
+registerTool('status_uptime', 'Daily uptime rollup for one provider with operational/degraded/down day counts and uptime % (degraded counts as half-credit). Costs 1 credit ($0.02). Strict premium, no free trial; the 7-day-capped sibling status_uptime_free is the discovery option.', {
     provider: z.string().describe('Provider name (e.g. anthropic, openai, google)'),
     from: z.string().optional().describe('Start date YYYY-MM-DD UTC (default: 30 days ago)'),
     to: z.string().optional().describe('End date YYYY-MM-DD UTC (default: today)'),

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tensorfeed/mcp-server",
-  "version": "1.36.1",
+  "version": "1.36.2",
   "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": "1.36.1",
+  "version": "1.36.2",
   "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": "1.36.1",
+      "version": "1.36.2",
       "runtimeHint": "npx",
       "transport": {
         "type": "stdio"
@@ -47,8 +47,13 @@
         "get_ai_status",
         "is_service_down",
         "get_model_pricing",
+        "get_model_deprecations",
         "get_ai_today",
         "get_agent_activity",
+        "get_ai_supply_chain_iocs",
+        "get_honeypot_iocs",
+        "check_afta_certification",
+        "get_agent_reputation_card",
         "mcp_registry_snapshot",
         "probe_latest",
         "get_ai_papers_trending",
@@ -87,7 +92,6 @@
         "provider_deepdive",
         "compare_models",
         "whats_new",
-        "mcp_registry_series",
         "probe_series",
         "list_watches",
         "create_price_watch",