# TensorFeed (npm · @tensorfeed/mcp-server)

AI news, model pricing, service status, and machine-payable premium tools. AFTA-certified.

- Trust score: 69/100 (medium)
- Change this week: +45
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.tensorfeed.ai`: 60/100, [markdown](https://verifymcp.io/servers/ai-tensorfeed-mcp-server/mcp.md), [page](https://verifymcp.io/servers/ai-tensorfeed-mcp-server/mcp)
- npm · `@tensorfeed/mcp-server`: 69/100 (this document), [markdown](https://verifymcp.io/servers/ai-tensorfeed-mcp-server/tensorfeed-mcp-server.md), [page](https://verifymcp.io/servers/ai-tensorfeed-mcp-server/tensorfeed-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@tensorfeed/mcp-server`
- Version: `2.0.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 27 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 4257 tokens (~170/item across 25 items; 24 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add ai-tensorfeed-mcp-server -- npx -y @tensorfeed/mcp-server
```

### Codex

```bash
codex mcp add ai-tensorfeed-mcp-server -- npx -y @tensorfeed/mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-tensorfeed-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@tensorfeed/mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-tensorfeed-mcp-server --command npx --arg -y --arg @tensorfeed/mcp-server
```

### Hermes

```yaml
mcp_servers:
  ai-tensorfeed-mcp-server:
    command: "npx"
    args: ["-y", "@tensorfeed/mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "ai-tensorfeed-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@tensorfeed/mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 69, +64)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Security disclosure: unverified → fail
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] License: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → 100
- [functional] Licence: MIT

### 2026-08-01 (score 5, −31)

- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional regression] Security disclosure: fail → unverified

### 2026-07-31 (score 36, +26)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 10, −70)

- [security regression] Known CVEs: partial → unverified
- [security regression] Malware scan: pass → unverified
- [security regression] Provenance: fail → unverified
- [security regression] Install scripts: pass → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional regression] Maintenance: pass → unverified
- [functional regression] License: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Licence: MIT

### 2026-07-28 (score 80, +56)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Schema quality: unverified → 100
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Schema quality: fail
- [functional] Licence: MIT

### 2026-07-27 (score 24)

First indexed and scored.

## MCP tools (24)

### `get_ai_news` (~184 tokens)

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.

Input parameters:

- `category` (string): Filter by category (e.g. "anthropic", "openai", "research", "tools")
- `digest` (boolean): When true, return a headline-only digest (title, source, URL per story) instead of the full article set.
- `limit` (number): Number of articles to return (default 10, max 50)

### `find_tensorfeed_data` (~176 tokens)

Discover which TensorFeed endpoint answers a data need. Describe what you want in plain language (e.g. "trending AI papers", "is OpenAI down", "model price history") and this returns the 2 to 3 best-matching TensorFeed endpoints, each with its HTTP path, what it returns, and whether it is free or paid. TensorFeed exposes 100+ AI-ecosystem data and signed-verdict endpoints; the core ones are also dedicated tools, but the full catalog is reachable here and callable over HTTP (paid ones via x402 or a credits token). Free, no auth. Use this first when no dedicated tool obviously fits.

Input parameters:

- `limit` (integer): Max endpoints to return (default 3).
- `query` (string, required): Plain-language description of the data or decision you need.

### `get_ai_status` (~91 tokens)

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.

### `is_service_down` (~143 tokens)

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.

Input parameters:

- `service` (string, required): Service name to check (e.g. "claude", "openai", "gemini", "mistral", "cohere", "hugging face", "replicate")

### `get_model_pricing` (~90 tokens)

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.

### `account_status` (~41 tokens)

Check the configured TensorFeed token: current credit balance plus recent per-endpoint usage (last 100 calls aggregated). Free, but requires TENSORFEED_TOKEN.

### `route_verdict` (~362 tokens)

TensorFeed's signed model-routing decision: the single best model for a task or named model, fused from live pricing, contamination-discounted benchmarks, real production usage, measured p95 latency, incident state, and deprecation flags, with the reasoning. tier='preview' (default) is free (10 calls per day per IP), top verdict only. tier='full' costs 1 credit ($0.02), adds ranked runners-up, constraint filters, and an AFTA-signed receipt you can audit, and needs a TENSORFEED_TOKEN. Get credits at tensorfeed.ai/developers/agent-payments.

Input parameters:

- `budget` (number): Full tier only. Max blended USD per 1M tokens.
- `exclude_deprecated` (boolean): Full tier only. Default true. Set false to keep deprecated or sunsetted models.
- `max_latency_p95_ms` (number): Full tier only. Drop candidates whose measured p95 latency exceeds this value (ms).
- `min_quality` (number): Full tier only. Minimum trust-discounted quality score in [0, 1].
- `model` (string): Model id or display name to narrow the verdict to one model (e.g. "Claude Opus 4.7" or "claude-opus-4-7"). Provide task or model.
- `require_operational` (boolean): Full tier only. Default true. Set false to keep candidates known down or in failover.
- `task` (string): Task type to route for (code, reasoning, creative, general). Provide task or model.
- `tier` (string): 'preview' (default, free) or 'full' (1 credit; adds runners-up, filters, signed receipt).

### `provider_reliability_verdict` (~191 tokens)

TensorFeed's signed dependability ruling over its OWN measured latency and availability probes of the frontier AI providers: the single most-dependable provider to build on and the riskiest, scoring availability and tail consistency (p50 over p95) equally because an agent retry loop feels the tail, not the median. tier='preview' (default) is free (10 calls per day per IP), top verdict only. tier='full' costs 1 credit ($0.02), adds the full per-provider ranking with measured availability and p50/p95/p99 and tail spread plus an AFTA-signed receipt, and needs a TENSORFEED_TOKEN. Get credits at tensorfeed.ai/developers/agent-payments.

Input parameters:

- `tier` (string): 'preview' (default, free) or 'full' (1 credit; adds the full per-provider ranking and signed receipt).

### `x402_settlement_verdict` (~228 tokens)

TensorFeed's signed ruling on the state of the x402 USDC settlement market on Base, computed over its OWN on-chain settlement index: market momentum versus the prior window of equal length, concentration, and the leading publisher. Covers the publishers TensorFeed indexes on Base, forward-only from launch. tier='preview' (default) is free (10 calls per day per IP), headline verdict only. tier='full' costs 1 credit ($0.02), adds the full per-publisher ranking with volume share, ecosystem totals, the Herfindahl concentration index, an optional window, and an AFTA-signed receipt, and needs a TENSORFEED_TOKEN. Get credits at tensorfeed.ai/developers/agent-payments.

Input parameters:

- `tier` (string): 'preview' (default, free) or 'full' (1 credit; adds per-publisher ranking, totals, window, signed receipt).
- `window` (string): Full tier only. Settlement window to rule over (24h, 7d, 30d). Default 7d.

### `x402_publisher_verdict` (~215 tokens)

TensorFeed's signed trust verdict on one x402 publisher, over its OWN on-chain settlement index: whether a named publisher domain is actively settling, recently quiet, registered with no settlement, unreachable, missing a Base payTo, or not indexed. Requires a domain. tier='preview' (default) is free (10 calls per day per IP), the trust verdict only. tier='full' costs 1 credit ($0.02), adds the 30-day settlement momentum, the shared-wallet risk flag, the settlement evidence (volume, count, last settled), and an AFTA-signed receipt, and needs a TENSORFEED_TOKEN. Get credits at tensorfeed.ai/developers/agent-payments.

Input parameters:

- `domain` (string, required): Publisher domain to rule on, e.g. "x402.tavily.com". Required.
- `tier` (string): 'preview' (default, free) or 'full' (1 credit; adds momentum, shared-wallet flag, evidence, signed receipt).

### `stack_safety_verdict` (~304 tokens)

TensorFeed's deploy gate for an AI software stack: pass each package as comma-separated name@version and get the overall BLOCK / HOLD / PASS / UNKNOWN gate plus a per-package verdict, fusing the ingested AI-stack CVE batch with the CISA KEV catalog. Conservative by design: BLOCK only on an exploited CVE with no fix, HOLD when a known CVE applies and you must verify your version, PASS on no match, UNKNOWN outside the curated AI-stack cohort. tier='preview' (default) is free (10 calls per day per IP), caps at 3 packages, gate plus worst offender. tier='full' costs 1 credit ($0.02), raises the cap to 10 packages, adds the matched-CVE evidence (ids, affected ranges, fixed versions, KEV status) and an AFTA-signed receipt, and needs a TENSORFEED_TOKEN. Get credits at tensorfeed.ai/developers/agent-payments.

Input parameters:

- `packages` (string, required): Comma-separated AI-stack packages as name@version (e.g. "vllm@0.5.0,transformers@4.40.0"). Required. Preview caps at 3, full up to 10.
- `tier` (string): 'preview' (default, free, caps at 3 packages) or 'full' (1 credit; up to 10 packages, matched-CVE evidence, signed receipt).

### `benchmark_trust_verdict` (~272 tokens)

TensorFeed's signed ruling on whether an AI benchmark is still a trustworthy capability signal or saturated, contaminated, or near ceiling so a high score should be down-weighted: a trust band (reliable, use_with_caution, saturated, contaminated, deprecated) and a 0-100 trust score per benchmark. Pass benchmark to narrow to one, or category to filter, or neither for the registry. tier='preview' (default) is free (10 calls per day per IP), top verdict and bands only. tier='full' costs 1 credit ($0.02), adds the per-signal detail (ceiling proximity, frontier compression, contamination), a down-weight recommendation with an alternative benchmark, and an AFTA-signed receipt, and needs a TENSORFEED_TOKEN. Get credits at tensorfeed.ai/developers/agent-payments.

Input parameters:

- `benchmark` (string): Benchmark registry id or name to narrow to one (e.g. "mmlu", "swe-bench"). Optional.
- `category` (string): Category to filter the benchmarks (e.g. "coding", "reasoning"). Optional.
- `tier` (string): 'preview' (default, free) or 'full' (1 credit; adds per-signal detail, recommendation, signed receipt).

### `failover_verdict` (~241 tokens)

Provider A is degraded; TensorFeed's signed ruling on the single best operational provider to fail over to for a task right now. Confirms A against the live incident-triage feed, then runs the route-verdict fusion with A (and any provider already in failover) excluded. Requires from. tier='preview' (default) is free (10 calls per day per IP), the failover target only. tier='full' costs 1 credit ($0.02), adds the full candidate (pricing, measured p95 latency, quality), the ranked alternatives, the confirmed incident on A, and an AFTA-signed receipt, and needs a TENSORFEED_TOKEN. Get credits at tensorfeed.ai/developers/agent-payments.

Input parameters:

- `from` (string, required): The degraded provider to fail over FROM (e.g. "anthropic", "openai"). Required.
- `task` (string): Task type to optimize the failover target for. Optional.
- `tier` (string): 'preview' (default, free) or 'full' (1 credit; adds candidate detail, ranked alternatives, incident, signed receipt).

### `ssvc_verdict` (~242 tokens)

TensorFeed's signed SSVC patch-urgency decision for one CVE, applying the CISA SSVC Coordinator decision tree to the recorded Vulnrichment decision points (exploitation, automatable, technical impact). Requires a CVE id. tier='preview' (default) is free (10 calls per day per IP): the three decision points and the decision-tree provenance, WITHOUT the computed Act / Attend / Track / Track* decision. tier='full' costs 1 credit ($0.02), adds the computed decision across the full low/medium/high Mission and Well-being envelope, the per-level reasoning, a live CISA KEV cross-check, and an AFTA-signed receipt, and needs a TENSORFEED_TOKEN. Get credits at tensorfeed.ai/developers/agent-payments.

Input parameters:

- `cve` (string, required): CVE id to rule on, e.g. "CVE-2024-3094". Required.
- `tier` (string): 'preview' (default, free) or 'full' (1 credit; adds the computed decision, envelope, reasoning, KEV cross-check, signed receipt).

### `pricing_series` (~143 tokens)

Daily price points for one AI model over a window. days 1 to 7 is free; days 8 to 90 costs 1 credit ($0.02) and needs a TENSORFEED_TOKEN, adding the min/max/delta summary over the longer window. Get credits at tensorfeed.ai/developers/agent-payments.

Input parameters:

- `days` (integer): Window length (default 7). 1 to 7 free; 8 to 90 costs 1 credit.
- `model` (string, required): Model id or display name (e.g. "Claude Opus 4.7" or "claude-opus-4-7").

### `benchmark_series` (~168 tokens)

Daily benchmark scores for one model+benchmark over a window. Benchmark keys: swe_bench, mmlu_pro, gpqa_diamond, math, human_eval. days 1 to 7 is free; days 8 to 90 costs 1 credit ($0.02) and needs a TENSORFEED_TOKEN, tracking score evolution over the longer window. Get credits at tensorfeed.ai/developers/agent-payments.

Input parameters:

- `benchmark` (string, required): Benchmark key (e.g. swe_bench, mmlu_pro, gpqa_diamond, math, human_eval).
- `days` (integer): Window length (default 7). 1 to 7 free; 8 to 90 costs 1 credit.
- `model` (string, required): Model id or display name.

### `status_uptime` (~145 tokens)

Daily uptime rollup for one provider over a window with operational/degraded/down day counts and uptime % (degraded counts as half-credit). days 1 to 7 is free; days 8 to 90 costs 1 credit ($0.02) and needs a TENSORFEED_TOKEN, adding per-incident-day detail over the longer window. Get credits at tensorfeed.ai/developers/agent-payments.

Input parameters:

- `days` (integer): Window length (default 7). 1 to 7 free; 8 to 90 costs 1 credit.
- `provider` (string, required): Provider name (e.g. anthropic, openai, google).

### `status_leaderboard` (~130 tokens)

Cross-provider uptime leaderboard ranked by uptime % DESC, computed from minute-resolution counters (~720 samples per provider per day). days 1 to 7 is free; days 8 to 90 costs 3 credits ($0.06) and needs a TENSORFEED_TOKEN, adding incident_count and mttr_minutes (mean time to recover) per provider over the longer window. Get credits at tensorfeed.ai/developers/agent-payments.

Input parameters:

- `days` (integer): Window length (default 7). 1 to 7 free; 8 to 90 costs 3 credits.

### `whats_new` (~95 tokens)

Catch up on everything that changed in AI in one call: pricing moves, new and removed models, status incidents, and top news from the last 1 to 7 days, so your agent boots with current context instead of stale assumptions. Costs 1 credit ($0.02).

Input parameters:

- `days` (number): Window length in days (default 1)
- `news_limit` (number): Max news headlines (default 10)

### `compare_models` (~122 tokens)

Pick between models in one call: pricing, benchmarks, status, and recent news for 2 to 5 models side by side, with cheapest-blended and per-benchmark rankings, so you choose without scraping each provider. Costs 1 credit ($0.02).

Input parameters:

- `ids` (string, required): Comma-separated list of 2-5 model ids or display names. Examples: "Claude Opus 4.8,GPT-5.5,Gemini 3.5 Flash" or "opus-4-8,gpt-5-5"

### `provider_deepdive` (~98 tokens)

Everything about one AI provider in a single call: live status, every model with pricing, tier, and benchmarks joined in, recent news, and agent traffic, replacing about four separate lookups. Costs 3 credits ($0.06). Strict premium, no free trial.

Input parameters:

- `provider` (string, required): Provider id or display name (case-insensitive). Examples: anthropic, openai, google, mistral, cohere

### `list_watches` (~31 tokens)

List the active webhook watches owned by the configured TensorFeed token. Free, requires TENSORFEED_TOKEN.

### `create_watch` (~417 tokens)

Register a webhook watch. type selects what to watch: "price" (a model price change), "status" (a service status transition), "digest" (a scheduled daily or weekly pricing summary), or "leaderboard_rank" (a provider crossing an uptime-rank threshold). Costs 1 credit ($0.02) at registration; the watch lives 90 days and each fire is an HMAC-signed POST to callback_url. Needs a TENSORFEED_TOKEN.

Input parameters:

- `cadence` (string): type=digest only. How often the digest fires.
- `callback_url` (string, required): HTTPS URL that receives the HMAC-signed POST when the watch fires.
- `field` (string): type=price only. Which price field to watch.
- `model` (string): type=price only. Model name (e.g. "Claude Opus 4.7").
- `op` (string): type=price uses lt/gt/changes (lt = below threshold, gt = above, changes = any change). type=status uses becomes/changes (becomes = transitions to a specific value; changes = any transition). type=le…
- `provider` (string): type=status or type=leaderboard_rank only. Provider name or slug (case-insensitive). e.g. anthropic, openai, gemini, bedrock, azure.
- `secret` (string): Optional shared secret used to HMAC-sign delivery bodies.
- `threshold` (number): type=price (when op is lt or gt) or type=leaderboard_rank (when op is drops_below or rises_above). Integer rank position for leaderboard_rank.
- `type` (string, required): What to watch.
- `value` (string): type=status only. Required when op is becomes.

### `delete_watch` (~47 tokens)

Delete one of your active webhook watches by id. Free, requires TENSORFEED_TOKEN.

Input parameters:

- `watch_id` (string, required): The wat_... id from create_watch / list_watches

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/ai-tensorfeed-mcp-server/tensorfeed-mcp-server#diagnostics

## Score history

- 2026-08-03: 69
- 2026-08-02: 69
- 2026-08-01: 5
- 2026-07-31: 36
- 2026-07-30: 10
- 2026-07-29: 80
- 2026-07-28: 80
- 2026-07-27: 24

## Links

- npm package: https://www.npmjs.com/package/@tensorfeed/mcp-server
- Socket report: https://socket.dev/npm/package/@tensorfeed/mcp-server
- Repository: https://github.com/RipperMercs/tensorfeed-mcp
- Website: https://tensorfeed.ai/developers/agent-payments
- Changelog RSS feed: https://verifymcp.io/servers/ai-tensorfeed-mcp-server/tensorfeed-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-tensorfeed-mcp-server/tensorfeed-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-tensorfeed-mcp-server/tensorfeed-mcp-server