Claude MarketplacesSubmit
rippermercs avatar

TensorFeed

rippermercs/tensorfeed-mcp

Plugs real-time AI ecosystem intel into Claude Desktop and any MCP client. Eight free tools give you same-day news from 36 sources, live service status for Anthropic/OpenAI/Google/Mistral, current model pricing across providers, measured API latency, and a snapshot of which AI bots are crawling the web right now. Premium tier adds fourteen paid tools (USDC on Base, pay per call) for smart model routing, price history series, cost projection across workloads, full-text news search, and webhook watches that fire when a price changes or a service goes down. AFTA-certified with no-charge guarantees on stale data and signed receipts. Useful when your agent needs to know what's broken, what's new, or which model to pick for a task today.

GitHub stars
1
tools
30
auth
Secret needed
transport
STDIO, HTTP
env var
1
last updated
Oct 30, 2026
View on GitHub

Install

From registry metadata
$ npx add-mcp https://mcp.tensorfeed.ai/mcp --name tensorfeed

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http tensorfeed https://mcp.tensorfeed.ai/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 30 tools

Verified live against the running server on Nov 6, 2026.

find_tensorfeed_dataDiscover 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 w...2 params

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 w...

Parameters* required
limitnumber
Max endpoints to return (1 to 5, default 3).
query*string
Plain-language description of the data or decision you need.
get_news_articlesGet 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 publish...2 params

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 publish...

Parameters* required
categorystring
Optional category filter (e.g. models, business, research)
limitnumber
Max articles to return (1-200)default: 25
get_status_summaryGet 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 | unknown per service, with the time each...

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 | unknown per service, with the time each...

No parameters. Call it with no arguments.

get_modelsGet 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 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.

No parameters. Call it with no arguments.

get_cve_recordLook 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.1 params

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.

Parameters* required
cve_id*string
CVE identifier in CVE-YYYY-NNNNN form, case-insensitive
get_kev_catalogGet 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.1 params

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.

Parameters* required
limitnumber
Top-N most-recent entries (1-50)default: 25
get_epss_scoreGet 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.1 params

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.

Parameters* required
cve_id*string
CVE identifier in CVE-YYYY-NNNNN form
get_osv_advisory_for_packageCross-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 2.0.3 params

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.

Parameters* required
ecosystem*string
OSV ecosystem identifier (PyPI, npm, Go, crates.io, etc)
name*string
Package name
versionstring
Optional package version
check_ai_supply_chain_riskCheck 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", ret...2 params

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", ret...

Parameters* required
ecosystemstring
Optional ecosystem filter: "npm" or "pip"
package_namestring
Optional case-insensitive substring of the package name (e.g. "mistralai" or "@mistralai/mistralai-gcp"). If omitted, returns all current entries.
check_agent_reputationLook 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), tr...2 params

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), tr...

Parameters* required
token_prefixstring
First 16 chars of a tf_live_ bearer token (e.g. "tf_live_18e54f47"). Mutually exclusive with wallet.
walletstring
EIP-55 or lowercased EOA wallet address (0x + 40 hex). Mutually exclusive with token_prefix.
submit_wantlist_itemSubmit 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.4 params

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.

Parameters* required
contact_optionalstring
Optional contact for follow-up. Leave blank to stay anonymous.
description*string
1 to 2 sentences explaining the use case. Max 500 chars.
request_typestring
What kind of thing you want. Defaults to "other" if omitted.one of data_source · endpoint · tool · mcp · integration · other
topic*string
Short label for the data category, e.g. "real estate records" or "crypto on-chain treasury"
register_free_watchRegister 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 del...4 params

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 del...

Parameters* required
callback_url*string
HTTPS URL to receive POST deliveries. Must NOT be private/localhost (SSRF guarded).
fire_capnumber
Optional cap on total fires for this watch. Capped at 25 for free tier; smaller values honored.
secretstring
Optional shared secret for HMAC-SHA256 signing. If omitted, TensorFeed generates a 32-hex secret and returns it once.
spec*object
Watch spec. Examples: { type: "price", model: "claude-opus-5-5", field: "blended", op: "lt", threshold: 50 }; { type: "status", provider: "openai", op: "becomes", value: "down" }; { type: "leaderbo...
search_sec_edgarLucene-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....5 params

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....

Parameters* required
enddtstring
End date YYYY-MM-DD
formsstring
Comma-separated form types (e.g. "10-K,10-Q,8-K")
limitnumber
Max hits (1-50)default: 10
q*string
Search query (Lucene syntax supported)
startdtstring
Start date YYYY-MM-DD
get_research_papersGet recent AI/ML research papers from one of three feeds, chosen with the source argument. arxiv_recent is the firehose: newest arXiv submissions in cs.AI / cs.LG / cs.CL / cs.CV by submission date, refreshed daily at 11:30 UTC. trending is citation-ranked from Semantic Schola...2 params

Get recent AI/ML research papers from one of three feeds, chosen with the source argument. arxiv_recent is the firehose: newest arXiv submissions in cs.AI / cs.LG / cs.CL / cs.CV by submission date, refreshed daily at 11:30 UTC. trending is citation-ranked from Semantic Schola...

Parameters* required
limitnumber
Max papers to return. Capped per source: arxiv_recent 50, trending 30, hf_daily 50.
source*string
Which feed to read. arxiv_recent = newest submissions (max 50). trending = citation-ranked (max 30). hf_daily = editor-curated with upvotes (max 50).one of arxiv_recent · trending · hf_daily
get_agent_opportunitiesGet 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, st...2 params

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, st...

Parameters* required
limitnumber
Max opportunities to return (1-25)default: 10
signalstring
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-pa...
route_verdictTensorFeed'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' is...9 params

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' is...

Parameters* required
budgetnumber
Full tier only. Max blended USD per 1M tokens.
exclude_deprecatedstring
Full tier only. Default true. Pass "false" to keep deprecated or sunsetted models.
max_latency_p95_msnumber
Full tier only. Drop candidates whose measured p95 latency exceeds this value (ms).
min_qualitynumber
Full tier only. Minimum quality in [0, 1] as a share of the best candidate measured on the same benchmark set (0.9 keeps models within 10 percent of the top).
modelstring
Model id or display name to narrow the verdict to one model (e.g. "Claude Opus 5.5" or "claude-opus-5-5"). Provide task or model.
paymentstring
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_operationalstring
Full tier only. Default true. Pass "false" to keep candidates known down or in failover.
taskstring
Task type to route for (code, reasoning, creative, general). Provide task or model.one of code · reasoning · creative · general
tierstring
'preview' (free, 10 calls per IP per day) or 'full' (1 credit; adds ranked runners-up, constraint filters, signed receipt). Omitted: preview, unless a payment or credits token is attached.one of preview · full
provider_reliability_verdictTensorFeed'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 retr...2 params

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 retr...

Parameters* required
paymentstring
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.
tierstring
'preview' (free, 10 calls per IP per day) or 'full' (1 credit; adds the full per-provider ranking and signed receipt). Omitted: preview, unless a payment or credits token is attached.one of preview · full
x402_settlement_verdictTensorFeed'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 B...3 params

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 B...

Parameters* required
paymentstring
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.
tierstring
'preview' (free, 10 calls per IP per day) or 'full' (1 credit; adds per-publisher ranking, totals, window, signed receipt). Omitted: preview, unless a payment or credits token is attached.one of preview · full
windowstring
Full tier only. Settlement window to rule over (24h, 7d, 30d). Default 7d.one of 24h · 7d · 30d
x402_publisher_verdictTensorFeed'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='pr...3 params

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='pr...

Parameters* required
domain*string
Publisher domain to rule on, e.g. "x402.tavily.com". Required.
paymentstring
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.
tierstring
'preview' (free, 10 calls per IP per day) or 'full' (1 credit; adds momentum, shared-wallet flag, evidence, signed receipt). Omitted: preview, unless a payment or credits token is attached.one of preview · full
stack_safety_verdictTensorFeed'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: BLO...3 params

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: BLO...

Parameters* required
packages*string
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.
paymentstring
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.
tierstring
'preview' (free, 10 calls per IP per day) or 'full' (1 credit; adds up to 10 packages, matched-CVE evidence, signed receipt; preview caps at 3 packages). Omitted: preview, unless a payment or credi...one of preview · full
benchmark_trust_verdictTensorFeed'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...4 params

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...

Parameters* required
benchmarkstring
Benchmark registry id or name to narrow to one (e.g. "mmlu", "swe-bench"). Optional.
categorystring
Category to filter the benchmarks (e.g. "coding", "reasoning"). Optional.
paymentstring
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.
tierstring
'preview' (free, 10 calls per IP per day) or 'full' (1 credit; adds per-signal detail, recommendation, signed receipt). Omitted: preview, unless a payment or credits token is attached.one of preview · full
failover_verdictProvider 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. Require...4 params

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. Require...

Parameters* required
from*string
The degraded provider to fail over FROM (e.g. "anthropic", "openai"). Required.
paymentstring
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.
taskstring
Task type to optimize the failover target for. Optional.one of code · reasoning · creative · general
tierstring
'preview' (free, 10 calls per IP per day) or 'full' (1 credit; adds candidate detail, ranked alternatives, incident, signed receipt). Omitted: preview, unless a payment or credits token is attached.one of preview · full
ssvc_verdictTensorFeed'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' is free (10 calls per day per IP): the th...3 params

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' is free (10 calls per day per IP): the th...

Parameters* required
cve*string
CVE id to rule on, e.g. "CVE-2024-3094". Required.
paymentstring
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.
tierstring
'preview' (free, 10 calls per IP per day) or 'full' (1 credit; adds the computed decision, envelope, reasoning, KEV cross-check, signed receipt). Omitted: preview, unless a payment or credits token...one of preview · full
pricing_seriesDaily price points for one AI model over a window. days 1 to 7 is free; days 8 to 90 costs 1 credit ($0.02), adding the min/max/delta summary over the longer window. tier='full' uses the paid tier at any window. Pay per call with an x402 wallet payment (arguments.payment, or a...4 params

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), adding the min/max/delta summary over the longer window. tier='full' uses the paid tier at any window. Pay per call with an x402 wallet payment (arguments.payment, or a...

Parameters* required
daysnumber
Window length in days (1 to 90, default 7). 1 to 7 free; 8 to 90 paid.
model*string
Model id or display name (e.g. "Claude Opus 5.5" or "claude-opus-5-5").
paymentstring
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.
tierstring
Optional. 'full' uses the paid tier even for a window of 7 days or less (adds the changes-detected count). Omit for the default split: days 1 to 7 free, 8 to 90 paid.one of full
benchmark_seriesDaily 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), tracking score evolution over the longer window. tier='full' uses the paid tier at any w...5 params

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), tracking score evolution over the longer window. tier='full' uses the paid tier at any w...

Parameters* required
benchmark*string
Benchmark key (e.g. swe_bench, mmlu_pro, gpqa_diamond, math, human_eval).
daysnumber
Window length in days (1 to 90, default 7). 1 to 7 free; 8 to 90 paid.
model*string
Model id or display name.
paymentstring
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.
tierstring
Optional. 'full' uses the paid tier even for a window of 7 days or less (adds the paid series envelope). Omit for the default split: days 1 to 7 free, 8 to 90 paid.one of full
status_uptimeDaily 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), adding per-incident-day detail over the longer window. tier='full' uses the pai...4 params

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), adding per-incident-day detail over the longer window. tier='full' uses the pai...

Parameters* required
daysnumber
Window length in days (1 to 90, default 7). 1 to 7 free; 8 to 90 paid.
paymentstring
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.
provider*string
Provider name (e.g. anthropic, openai, google).
tierstring
Optional. 'full' uses the paid tier even for a window of 7 days or less (adds per-incident-day detail). Omit for the default split: days 1 to 7 free, 8 to 90 paid.one of full
status_leaderboardCross-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 5 credits ($0.10), adding incident_count and mttr_minutes (mean time to recover) per provider over t...3 params

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 5 credits ($0.10), adding incident_count and mttr_minutes (mean time to recover) per provider over t...

Parameters* required
daysnumber
Window length in days (1 to 90, default 7). 1 to 7 free; 8 to 90 costs 5 credits.
paymentstring
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.
tierstring
Optional. 'full' uses the paid tier even for a window of 7 days or less (adds incident_count and mttr_minutes per provider). Omit for the default split: days 1 to 7 free, 8 to 90 paid.one of full
whats_newPREMIUM (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 headl...4 params

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 headl...

Parameters* required
daysnumber
Lookback window in days. Default 1.
news_limitnumber
Maximum headlines returned. Default 10.
paymentstring
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.
sincestring
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 someth...
compare_modelsPREMIUM (1 credit, $0.02). 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. Pay per call with an x402 wallet payment (ar...2 params

PREMIUM (1 credit, $0.02). 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. Pay per call with an x402 wallet payment (ar...

Parameters* required
ids*string
Comma-separated list of 2-5 model ids or display names. Examples: "Claude Opus 5.5,GPT-6.1 Sol,Claude Haiku 5.5" or "opus-5-5,gpt-6-1-sol,haiku-5-5"
paymentstring
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.
provider_deepdivePREMIUM (5 credits, $0.10). 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. Strict premium, no free trial. Pay per call with an x402...2 params

PREMIUM (5 credits, $0.10). 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. Strict premium, no free trial. Pay per call with an x402...

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

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Configuration

TENSORFEED_TOKENsecret

Bearer token from /api/payment/buy-credits. Required for paid tiers (full verdicts, 8 to 90 day series, webhook watches, account status). Free tiers (news, status, pricing, verdict previews, 1 to 7 day series, model discovery) work without it. Buy credits in USDC on Base at https

Readme

TensorFeed MCP Server

npm version MCP Registry License: MIT AFTA Certified HF Dataset

The official Model Context Protocol server for TensorFeed.ai. Plugs into Claude Desktop, Claude Code, Cursor, and any MCP-compatible client. Gives your agent real-time AI ecosystem data through 24 sharp tools: free data tools, eight signed verdict decisions with free previews, and premium tools paid per call in USDC on Base.

View the full README on GitHub

Details

Repository
github.com/rippermercs/tensorfeed-mcp
Website
tensorfeed.ai/developers/agent-payments
Package
@tensorfeed/mcp-server
Transport
STDIO, HTTP
Auth
Required
Registry
MCP registry, active
Tools verified
Nov 6, 2026

More from rippermercs