# TensorFeed (remote · mcp.tensorfeed.ai)

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

- Trust score: 60/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.tensorfeed.ai`: 60/100 (this document), [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, [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

- Endpoint: `https://mcp.tensorfeed.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 33 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 5754 tokens (~174/item across 33 items; 33 tools + 0 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**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-tensorfeed-mcp-server https://mcp.tensorfeed.ai/mcp
```

### Codex

```toml
[mcp_servers.ai-tensorfeed-mcp-server]
url = "https://mcp.tensorfeed.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-tensorfeed-mcp-server": {
      "type": "remote",
      "url": "https://mcp.tensorfeed.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-tensorfeed-mcp-server --url https://mcp.tensorfeed.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-tensorfeed-mcp-server:
    url: "https://mcp.tensorfeed.ai/mcp"
```

### Other

```json
{
  "mcpServers": {
    "ai-tensorfeed-mcp-server": {
      "type": "http",
      "url": "https://mcp.tensorfeed.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-08-03 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 58, 0)

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

### 2026-07-30 (score 58, 0)

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

### 2026-07-29 (score 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 56, 0)

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

### 2026-07-26 (score 56)

First indexed and scored.

## MCP tools (33)

### `get_news_articles` (~112 tokens)

Get the latest AI news articles aggregated from 12+ sources (Anthropic, OpenAI, Google, HuggingFace, TechCrunch, The Verge, Hacker News, etc). Polled every 10 min, deduplicated, sanitized for prompt injection. Returns up to 200 articles with title, snippet, source, and publishedAt.

Input parameters:

- `category` (string): Optional category filter (e.g. models, business, research)
- `limit` (number): Max articles to return (1-200)

### `get_status_summary` (~76 tokens)

Get the live operational status of every major AI service tracked by TensorFeed (Claude, ChatGPT, Gemini, Perplexity, Cohere, Mistral, HuggingFace, Replicate, Midjourney, etc). Polled every 2 min. Returns operational | degraded | down per service plus the most recent incident.

### `get_models` (~56 tokens)

Get the model pricing and specs catalog across providers (Anthropic, OpenAI, Google, Meta, Mistral, Cohere, etc). Includes per-token pricing, context windows, capabilities, deprecation flags. Refreshed daily.

### `get_cve_record` (~99 tokens)

Look up a single CVE Record v5.2 from the MITRE CVE List by ID (e.g. CVE-2024-3094). Lazy-fetched and cached 7 days. License: MITRE CVE Terms of Use, commercial redistribution permitted; the response includes the standard attribution block.

Input parameters:

- `cve_id` (string, required): CVE identifier in CVE-YYYY-NNNNN form, case-insensitive

### `get_kev_catalog` (~81 tokens)

Get the CISA Known Exploited Vulnerabilities (KEV) catalog. Returns the most recent N entries plus catalog metadata. Refreshed daily at 06:30 UTC. License: US Government public domain. ~1500 actively-exploited CVEs.

Input parameters:

- `limit` (number): Top-N most-recent entries (1-50)

### `get_epss_score` (~90 tokens)

Get the EPSS (Exploit Prediction Scoring System) probability for one CVE, sourced from FIRST.org. Returns the daily probability (0-1) that the CVE will be exploited in the next 30 days plus a percentile rank. License: FIRST.org free-for-any-use.

Input parameters:

- `cve_id` (string, required): CVE identifier in CVE-YYYY-NNNNN form

### `get_osv_advisory_for_package` (~120 tokens)

Cross-ecosystem vulnerability advisory lookup via OSV.dev. Given an ecosystem (PyPI, npm, Go, crates.io, Maven, NuGet, RubyGems, Packagist, etc) and a package name (optional version), returns advisories affecting that package. License: Apache 2.0.

Input parameters:

- `ecosystem` (string, required): OSV ecosystem identifier (PyPI, npm, Go, crates.io, etc)
- `name` (string, required): Package name
- `version` (string): Optional package version

### `get_osv_advisory_by_id` (~108 tokens)

Look up a single OSV.dev advisory by ID. Accepts GHSA / CVE / PYSEC / RUSTSEC / GO / OSV / DSA / ALPINE / DEBIAN / UBUNTU and other documented identifier prefixes. License: Apache 2.0.

Input parameters:

- `id` (string, required): Advisory ID, e.g. GHSA-r75f-5x8p-qvmc or CVE-2024-3094

### `check_ai_supply_chain_risk` (~185 tokens)

Check the TensorFeed AI/MCP/LLM supply-chain IOC feed. Returns publicly-disclosed malicious npm/PyPI packages whose name or summary signals relevance to AI agent operators. With no args, returns the whole snapshot (typically a small number of entries). With "package_name", returns only entries matching that name (substring, case-insensitive) so an agent can ask "is X risky right now?" before installing. Each entry cites its GHSA primary source. Posture: TF republishes already-public advisories; the listed primary source is authoritative.

Input parameters:

- `ecosystem` (string): Optional ecosystem filter: "npm" or "pip"
- `package_name` (string): Optional case-insensitive substring of the package name (e.g. "mistralai" or "@mistralai/mistralai-gcp"). If omitted, returns all current entries.

### `check_agent_reputation` (~274 tokens)

Look up an agent's public reputation card from the TensorFeed Agent Reputation Bureau. Takes a wallet (0x + 40 hex) OR a token_prefix (first 16 chars of a tf_live_ bearer). Returns the full ReputationCard: composite + sub-metric ranks (reliability, spend, activity, streak), trust grade A through F, public flags (new_wallet, spend_spike, claim_disputed, etc), wallet age, first_seen, last_active, ofac_clean, banned + ban_reason if applicable. Cards rebuild daily at 04:50 UTC from TF's own observable telemetry. Returns ok=false with status=not_found for unknown identities so callers can distinguish "we have no record" from "we have a record showing zero activity". Useful for: marketplaces routing work to high-grade agents, peer agents deciding to trust another agent, ops dashboards monitoring an agent's standing, or operators inspecting their own reputation before claiming a wallet.

Input parameters:

- `token_prefix` (string): First 16 chars of a tf_live_ bearer token (e.g. "tf_live_18e54f47"). Mutually exclusive with wallet.
- `wallet` (string): EIP-55 or lowercased EOA wallet address (0x + 40 hex). Mutually exclusive with token_prefix.

### `search_agent_directory` (~347 tokens)

Search the TensorFeed Agent Self-Directory for hireable AI agents. Filter by skill (from a controlled vocab including research, data-analysis, coding, content-writing, voice-acting, image-generation, etc), service_area (research/data/coding/writing/voice/image/video/other), language (BCP 47), availability, hourly rate cap, minimum years of experience, or verified-hireable status. Verified-hireable members (operators paying $5 USDC/30 days for top-tier visibility) sort first. Free tier capped at 25 results. Returns wallet, display_name, operator_url, skills, rates, languages, years_experience, composite reputation rank, trust grade. TF publishes self-descriptions; TF takes no fee from off-platform transactions between operators and the agents who contact them.

Input parameters:

- `available` (boolean): Only operators self-declaring as available_for_hire.
- `language` (string): BCP 47 language code (e.g. en, ja, es-MX).
- `limit` (number): Max results to return (1-25, default 25).
- `max_rate` (number): Maximum hourly_rate_max_usd (operators with no rate set are NOT filtered out).
- `min_experience` (number): Minimum years_experience (operators with no value set ARE filtered out).
- `service_area` (string): Filter by service_area (research|data|coding|writing|voice|image|video|other).
- `skill` (string): Filter by a single skills_tag (must be in controlled vocab).
- `verified` (boolean): Only verified-hireable operators (active $5/30d badge).

### `get_verified_hireable_status` (~107 tokens)

Look up whether a specific wallet has an active verified-hireable subscription on the TensorFeed Agent Directory. Returns { verified_hireable: bool, verified_hireable_until?: ISO } for a given wallet. Useful for downstream marketplaces or peer agents who want to confirm a published-rate or active-availability badge is current before routing work to that wallet.

Input parameters:

- `wallet` (string, required): EIP-55 or lowercased wallet address (0x + 40 hex).

### `list_directory_skills` (~60 tokens)

Return the distribution of skill tags across all active operator claims on the TensorFeed Agent Directory. Sorted by count desc. Useful for agents discovering what kinds of work other operators advertise on TF, OR for agent-marketplaces wanting to mirror TF's controlled vocab.

### `check_free_tier_status` (~85 tokens)

Check the caller IP's free premium-API trial quota. TensorFeed gives 100 free /api/premium/* calls per IP per 24h rolling window with no auth required. This tool returns used_today, remaining, and resets_at without consuming a quota slot. Use it before deciding whether to make a paid call versus waiting for the trial reset. No arguments.

### `submit_wantlist_item` (~161 tokens)

Submit a wantlist entry telling TensorFeed what data you wish was served. Aggregated patterns inform TF's pipeline priorities. Anonymous by default, no PII collected, items expire after 30 days. Per-IP rate limit 5 submissions per 24h. Signal collector, not a contract.

Input parameters:

- `contact_optional` (string): Optional contact for follow-up. Leave blank to stay anonymous.
- `description` (string, required): 1 to 2 sentences explaining the use case. Max 500 chars.
- `request_type` (string): What kind of thing you want. Defaults to "other" if omitted.
- `topic` (string, required): Short label for the data category, e.g. "real estate records" or "crypto on-chain treasury"

### `register_free_watch` (~350 tokens)

Register a free webhook subscription. TensorFeed POSTs HMAC-signed deliveries to your callback_url when the watch spec fires (price drop, status change, leaderboard rank shift, macro indicator threshold crossing, etc). 5 watches per IP, 25 fires per watch, 30-day TTL. Same delivery infrastructure as paid /api/premium/watches. If you omit secret, TensorFeed generates one and returns it; you cannot retrieve it again later. Same IP for management; manage via the REST endpoints under /api/watches/free/{id}.

Input parameters:

- `callback_url` (string, required): HTTPS URL to receive POST deliveries. Must NOT be private/localhost (SSRF guarded).
- `fire_cap` (number): Optional cap on total fires for this watch. Capped at 25 for free tier; smaller values honored.
- `secret` (string): Optional shared secret for HMAC-SHA256 signing. If omitted, TensorFeed generates a 32-hex secret and returns it once.
- `spec` (object, required): Watch spec. Examples: { type: "price", model: "opus-4-7", field: "blended", op: "lt", threshold: 50 }; { type: "status", provider: "openai", op: "becomes", value: "down" }; { type: "leaderboard_rank"…

### `search_sec_edgar` (~178 tokens)

Lucene-style full-text search across the entire SEC EDGAR public-filings corpus since the 1990s. Forms include 10-K (annual), 10-Q (quarterly), 8-K (current event), DEF 14A (proxy), S-1 (IPO), 13F (institutional holdings), and ~70+ others. License: US Government public domain. The killer endpoint for finance and equity-research agents.

Input parameters:

- `enddt` (string): End date YYYY-MM-DD
- `forms` (string): Comma-separated form types (e.g. "10-K,10-Q,8-K")
- `limit` (number): Max hits (1-50)
- `q` (string, required): Search query (Lucene syntax supported)
- `startdt` (string): Start date YYYY-MM-DD

### `get_sec_submissions` (~110 tokens)

Get entity metadata + recent filings for one company by CIK. Accepts canonical zero-padded CIK ("0000320193"), bare numeric ("320193"), or "CIK0000320193" prefixed. Returns full company profile (name, tickers, exchanges, EIN, SIC, addresses) plus the most-recent ~1000 filings. License: US Government public domain.

Input parameters:

- `cik` (string, required): CIK in any zero-padding form, or CIK-prefixed

### `lookup_sec_company_ticker` (~91 tokens)

Resolve a stock ticker symbol (e.g. AAPL, MSFT, NVDA) or numeric CIK to the canonical SEC entity record. Returns ticker, CIK, company name, and exchange. Pair with get_sec_submissions to retrieve filings. License: US Government public domain.

Input parameters:

- `ticker_or_cik` (string, required): Ticker symbol (case-insensitive) or numeric CIK

### `query_fda_drug_events` (~197 tokens)

Query the FDA FAERS adverse event reports database. Returns drug-event records with patient demographics, drug names, reaction terms (MedDRA-coded), outcomes, and seriousness flags. Uses openFDA Lucene-style search syntax (e.g. "patient.drug.medicinalproduct:aspirin"). License: openFDA CC0 1.0 Universal Dedication, FDA waiver of all copyright; commercial redistribution permitted.

Input parameters:

- `limit` (number): Max records to return (1-100)
- `search` (string): openFDA Lucene-style search expression. Examples: patient.drug.medicinalproduct:aspirin, patient.reaction.reactionmeddrapt:headache+AND+receivedate:[20240101+TO+20251231]
- `skip` (number): Pagination offset (0-25000)
- `sort` (string): Sort by field (e.g. receivedate:desc)

### `query_fda_drug_labels` (~136 tokens)

Query the FDA structured product labeling (SPL) database for prescription and OTC drugs. Returns indications, dosage, warnings, contraindications, adverse reactions, and pharmacology sections. License: openFDA CC0 1.0; commercial redistribution permitted.

Input parameters:

- `limit` (number): Max records to return (1-100)
- `search` (string): openFDA Lucene-style search expression. Examples: openfda.brand_name:tylenol, openfda.generic_name:metformin
- `skip` (number): Pagination offset (0-25000)
- `sort` (string): Sort by field

### `query_fda_drug_recalls` (~140 tokens)

Query the FDA drug enforcement (recall) database. Returns recall classification (Class I/II/III), reason, distribution, product description, and voluntary/mandatory flag. License: openFDA CC0 1.0; commercial redistribution permitted.

Input parameters:

- `limit` (number): Max records to return (1-100)
- `search` (string): openFDA Lucene-style search expression. Examples: classification:"Class+I", reason_for_recall:contamination
- `skip` (number): Pagination offset (0-25000)
- `sort` (string): Sort by field (e.g. report_date:desc)

### `query_fda_food_recalls` (~128 tokens)

Query the FDA food enforcement (recall) database covering food products distributed in the US. Same shape as drug recalls. License: openFDA CC0 1.0; commercial redistribution permitted.

Input parameters:

- `limit` (number): Max records to return (1-100)
- `search` (string): openFDA Lucene-style search expression. Examples: reason_for_recall:listeria, classification:"Class+I"
- `skip` (number): Pagination offset (0-25000)
- `sort` (string): Sort by field (e.g. report_date:desc)

### `query_fda_device_events` (~133 tokens)

Query the FDA MAUDE medical device adverse event reports database. Returns device identifiers, problem codes, event narratives, patient outcomes. Useful for safety signal detection on FDA-cleared devices. License: openFDA CC0 1.0; commercial redistribution permitted.

Input parameters:

- `limit` (number): Max records to return (1-100)
- `search` (string): openFDA Lucene-style search expression. Examples: device.brand_name:medtronic, device.generic_name:pacemaker
- `skip` (number): Pagination offset (0-25000)
- `sort` (string): Sort by field

### `get_eia_series` (~181 tokens)

Get a US Energy Information Administration time-series. Curated routes: petroleum/pri/spt (WTI/Brent crude spot prices), petroleum/pri/gnd (US retail gasoline), natural-gas/pri/sum (Henry Hub + retail nat gas), electricity/retail-sales (by state and sector), electricity/electric-power-operational-data (net generation by fuel), total-energy. License: US Government public domain.

Input parameters:

- `end` (string): End date YYYY-MM-DD
- `length` (number): Max records (1-5000)
- `route` (string, required): One of: petroleum/pri/spt, petroleum/pri/gnd, natural-gas/pri/sum, electricity/retail-sales, electricity/electric-power-operational-data, total-energy
- `start` (string): Start date YYYY-MM-DD

### `get_arxiv_recent` (~148 tokens)

Get the 50 most recent arXiv submissions in cs.AI / cs.LG / cs.CL / cs.CV, sorted by submission date. Each entry carries arxivId (no version suffix), version, title, abstract, authors, primary category, all categories, publishedAt, updatedAt, htmlUrl, pdfUrl, and doi. Refreshed daily at 11:30 UTC. The firehose pair to get_ai_trending_papers (which ranks by citation count). License: arXiv permits use of metadata; the standard attribution block ships on every response.

Input parameters:

- `limit` (number): Max papers to return (1-50). Default 25.

### `get_ai_trending_papers` (~154 tokens)

Get the daily curated AI/ML trending papers from Semantic Scholar, ranked by citation count. Five fan-out queries (large language model, transformer, RLHF, AI agents, diffusion model), deduped by paperId, top 30 returned. Each entry carries paperId, title, abstract, authors, year, venue, citationCount, arxivId, doi, and fieldsOfStudy. Refreshed daily at 11:00 UTC. Citation-ranked counterpart to get_arxiv_recent (firehose by submission date). License: Semantic Scholar API permits use; the standard attribution block ships on every response.

Input parameters:

- `limit` (number): Max papers to return (1-30). Default 15.

### `get_hf_daily_papers` (~137 tokens)

Get Hugging Face's editor-curated daily AI/ML papers feed with community upvotes and discussion counts. Each entry carries paperId, title (sanitized), summary, authors, publishedAt, submittedAt, upvotes, num_comments, thumbnail, hf_url, arxiv_url (when arxiv-style), github_repo, github_stars, ai_keywords. Different signal from get_arxiv_recent (firehose) and get_ai_trending_papers (citation-ranked). Refreshed daily at 14:15 UTC.

Input parameters:

- `limit` (number): Max papers to return (1-50). Default 20.

### `get_weather_alerts` (~281 tokens)

Get active US weather alerts from the National Weather Service. US-only coverage. Filter by 2-letter state code (area), exact event name (e.g. 'Tornado Warning', 'Heat Advisory'), severity (Extreme | Severe | Moderate | Minor | Unknown), urgency (Immediate | Expected | Future | Past | Unknown), and status (actual | exercise | system | test | draft). Returns a flattened alerts list with id, event, severity, urgency, headline, description, areaDesc, sent/effective/expires/ends, sender_name, web URL. Refreshed in real time upstream; cached 60s. License: US Government public domain (17 USC §105).

Input parameters:

- `area` (string): 2-letter US state or territory code (CA, TX, PR, etc). Optional.
- `event` (string): Exact NWS event name (e.g. "Tornado Warning", "Heat Advisory"). Optional.
- `limit` (number): Max alerts to return (1-500). Default 50.
- `severity` (string): One of: Extreme, Severe, Moderate, Minor, Unknown. Optional.
- `status` (string): One of: actual, exercise, system, test, draft. Optional.
- `urgency` (string): One of: Immediate, Expected, Future, Past, Unknown. Optional.

### `get_recent_earthquakes` (~197 tokens)

Get recent earthquakes from the US Geological Survey's pre-built summary feeds. Choose a magnitude bucket (significant | 4.5 | 2.5 | 1.0 | all) and a time window (hour | day | week | month). Returns a flattened list with id, magnitude, place, time (ISO 8601), depth_km, longitude, latitude, tsunami flag, USGS detail URL. Upstream feeds refresh every minute. License: US Government public domain (17 USC §105).

Input parameters:

- `limit` (number): Max earthquakes to return (1-500). Default 50.
- `magnitude` (string): Magnitude bucket. One of: significant, 4.5, 2.5, 1.0, all. Default 4.5.
- `period` (string): Time window. One of: hour, day, week, month. Default day.

### `get_agent_opportunities` (~226 tokens)

Get TensorFeed's daily scan of new repositories across the AI agent ecosystem (Anthropic, OpenAI, Microsoft, ModelContextProtocol, HuggingFace, LangChain, frontier labs) plus recent MCP/x402/skills keyword sweeps. Each opportunity includes the GitHub repo path, description, stars, last update, the source signal, and a composite score (signal weight × log10(stars+1) × recency decay). Refreshed daily at 13:30 UTC. Useful for surfacing distribution targets, integration ideas, or just a daily digest of what's launching across the agent space. License: GitHub data via the public Search API; output is TensorFeed's curated ranking.

Input parameters:

- `limit` (number): Max opportunities to return (1-25)
- `signal` (string): Optional filter to one signal source. One of: anthropic-org, openai-org, microsoft-org, mcp-org, huggingface-org, langchain-org, frontier-labs, mcp-keyword, x402-keyword, skill-keyword, vertical-patt…

### `route_verdict` (~334 tokens)

PREMIUM (1 credit, $0.02). The signed model-routing decision: for a task (code, reasoning, creative, general) or a named model, returns the single best model to use right now, fusing pricing, benchmark capability discounted for contamination, real production usage, measured p95 latency, and live operational state, with runners-up and an AFTA-signed receipt over the inputs. Pay per call with an x402 wallet payment (arguments.payment, or an X-PAYMENT header; strict HTTP-402 transport at https://mcp.tensorfeed.ai/mcp?x402=strict) or use an Authorization: Bearer tf_live_... credits token. No token and no USDC? Claim free trial credits by signing a wallet message at https://tensorfeed.ai/api/payment/trial-credits.

Input parameters:

- `exclude_deprecated` (string): Default true. Pass "false" to keep deprecated or sunsetted models.
- `max_latency_p95_ms` (number): Drop candidates whose measured p95 latency exceeds this floor.
- `model` (string): Canonical model id or display name to narrow the verdict to one model.
- `payment` (string): Optional base64 x402 payment payload (the same string an X-PAYMENT header would carry). Sign against the accepts[0] requirement returned by an unpaid call. Alternative to the Bearer credits token.
- `require_operational` (string): Default true. Pass "false" to keep candidates known down or in failover.
- `task` (string): One of code, reasoning, creative, general. Provide task or model.

### `whats_new` (~344 tokens)

PREMIUM (1 credit, $0.02). The full TensorFeed morning brief: every AI headline in the window with links, model pricing deltas, and incident detail, AFTA-signed. The free preview sibling (/api/preview/whats-new, 10 calls/IP/day) returns only summary counts plus the top 3 headline titles; this paid call returns the complete brief with no rate limit. Pay per call with an x402 wallet payment (arguments.payment, or an X-PAYMENT header; strict HTTP-402 transport at https://mcp.tensorfeed.ai/mcp?x402=strict) or use an Authorization: Bearer tf_live_... credits token. No token and no USDC? Claim free trial credits by signing a wallet message at https://tensorfeed.ai/api/payment/trial-credits. Returning caller? Pass since=<cursor> from your last brief and an unchanged poll is free (no credit charged); you pay only when something new has broken since that cursor.

Input parameters:

- `days` (number): Lookback window in days. Default 1.
- `news_limit` (number): Maximum headlines returned. Default 10.
- `payment` (string): Optional base64 x402 payment payload (the same string an X-PAYMENT header would carry). Sign against the accepts[0] requirement returned by an unpaid call. Alternative to the Bearer credits token.
- `since` (string): Cursor from your last paid brief (returned as the `poll` continuation on every paid call). Pass it back and an unchanged poll returns for free: no credit is charged. You are billed only when somethin…

## Diagnostics

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

## Score history

- 2026-08-03: 60
- 2026-08-02: 59
- 2026-08-01: 59
- 2026-07-31: 58
- 2026-07-30: 58
- 2026-07-29: 58
- 2026-07-28: 57
- 2026-07-27: 56
- 2026-07-26: 56

## Links

- Remote endpoint: https://mcp.tensorfeed.ai/mcp
- 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/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-tensorfeed-mcp-server/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-tensorfeed-mcp-server/mcp