TensorFeed MCP server
ai.tensorfeed/mcp-servertensorfeed.aistreamable-httpv2.1.0Scanned
AI news, model pricing, service status, and machine-payable premium tools. AFTA-certified.
30 tools: 17 change things and 13 only read.
- Reads private data · 2
- Reads text others write · 1
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
17 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the TensorFeed MCP server can do
The TensorFeed MCP server is published by tensorfeed.ai, a domain the MCP Registry verified. It has 30 tools. It can create or change data (17 tools: ask_tensorfeed, check_ai_supply_chain_risk, check_agent_reputation, submit_wantlist_item and 13 more), but cannot delete data. 13 tools only read.
2 tools read private data (get_status_summary and get_agent_opportunities); 1 tool brings in text other people can write (get_status_summary); 1 tool can send data out of your system (register_free_watch). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 2.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
30 tools
Changes things 17Claude Code: ask
ask_tensorfeedAsk TensorFeed a plain-language question about AI models, providers, or AI security and get the answer itself, not a list of endpoints.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Ask TensorFeed a plain-language question about AI models, providers, or AI security and get the answer itself, not a list of endpoints. Answers from free live data: the best or cheapest model for a task (coding, reasoning, writing), one model's price, context window, and specs, two models side by side, whether an AI provider or service is down right now, the latest AI news on a topic, upcoming model deprecations and shutdowns, and CVE or CISA KEV lookups including AI packages like vllm. Returns answer (one or two sentences), data (the supporting slice), sources (endpoint plus a tensorfeed.ai page_url to cite), next (1 to 3 follow-up calls; paid ones carry their price and what they add), intent, and confidence. When no direct answer applies it says so and returns the best-matching TensorFeed tools and endpoints instead. Free, no auth. Examples: "cheapest model for coding with vision", "is OpenAI down right now?". Use this first for any AI model, pricing, status, news, or security question.
benchmark_seriesDaily benchmark scores for one model+benchmark over a window.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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 window. 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.
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: …No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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' is free (10 calls per day per IP), top verdict and bands only. tier='full' costs 1 credit ($0.02) and adds the per-signal detail (ceiling proximity, frontier compression, contamination), a down-weight recommendation with an alternative benchmark, and an AFTA-signed receipt. Omit tier and you get the free preview, unless the call carries a payment or credits token (or uses the strict x402 transport), in which case it bills as full. 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.
check_agent_reputationLook up an agent's public reputation card from the TensorFeed Agent Reputation Bureau.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
check_ai_supply_chain_riskCheck the TensorFeed AI/MCP/LLM supply-chain IOC feed.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
failover_verdictProvider A is degraded; TensorFeed's signed ruling on the single best operational provider to fail over to for a task right now.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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' is free (10 calls per day per IP), the failover target only. tier='full' costs 1 credit ($0.02) and adds the full candidate (pricing, measured p95 latency, quality), the ranked alternatives, the confirmed incident on A, and an AFTA-signed receipt. Omit tier and you get the free preview, unless the call carries a payment or credits token (or uses the strict x402 transport), in which case it bills as full. 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.
pricing_seriesDaily price points for one AI model over a window.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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 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.
provider_deepdivePREMIUM (5 credits, $0.10).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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 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.
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…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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' is free (10 calls per day per IP), top verdict only. tier='full' costs 1 credit ($0.02) and adds the full per-provider ranking with measured availability and p50/p95/p99 and tail spread plus an AFTA-signed receipt. Omit tier and you get the free preview, unless the call carries a payment or credits token (or uses the strict x402 transport), in which case it bills as full. 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.
register_free_watchRegister a free webhook subscription.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.callback_url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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}.
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, me…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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 free (10 calls per day per IP), top verdict only. tier='full' costs 1 credit ($0.02) and adds ranked runners-up, constraint filters, and an AFTA-signed receipt you can audit. Omit tier and you get the free preview, unless the call carries a payment or credits token (or uses the strict x402 transport), in which case it bills as full. 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.
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, automatabl…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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 three decision points and the decision-tree provenance, WITHOUT the computed Act / Attend / Track / Track* decision. tier='full' costs 1 credit ($0.02) and 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. Omit tier and you get the free preview, unless the call carries a payment or credits token (or uses the strict x402 transport), in which case it bills as full. 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.
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 verdi…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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' 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, and adds the matched-CVE evidence (ids, affected ranges, fixed versions, KEV status) and an AFTA-signed receipt. Omit tier and you get the free preview, unless the call carries a payment or credits token (or uses the strict x402 transport), in which case it bills as full. 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.
submit_wantlist_itemSubmit a wantlist entry telling TensorFeed what data you wish was served.No findings
Why it is in this group
- The name "submit_wantlist_item" says "submit": a word for a change.
Description, as the server wrote it 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.
whats_newPREMIUM (1 credit, $0.02).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
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 w…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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' is free (10 calls per day per IP), the trust verdict only. tier='full' costs 1 credit ($0.02) and adds the 30-day settlement momentum, the shared-wallet risk flag, the settlement evidence (volume, count, last settled), and an AFTA-signed receipt. Omit tier and you get the free preview, unless the call carries a payment or credits token (or uses the strict x402 transport), in which case it bills as full. 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.
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 equa…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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' is free (10 calls per day per IP), headline verdict only. tier='full' costs 1 credit ($0.02) and adds the full per-publisher ranking with volume share, ecosystem totals, the Herfindahl concentration index, an optional window, and an AFTA-signed receipt. Omit tier and you get the free preview, unless the call carries a payment or credits token (or uses the strict x402 transport), in which case it bills as full. 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.
Only reads 13Show 13 read-only tools
compare_modelsPREMIUM (1 credit, $0.02).No findings
Why it is in this group
- The name "compare_models" says "compare": a word for reading.
Description, as the server wrote it 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 (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.
get_agent_opportunitiesGet TensorFeed's daily scan of new repositories across the AI agent ecosystem (Anthropic, OpenAI, Microsoft, ModelContextProtocol, HuggingFace, LangChain, frontier labs) plus recen…Reads private dataNo findings
Why it is in this group
- The name "get_agent_opportunities" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "repository": it reads repositories.
Description, as the server wrote it 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.
get_cve_recordLook up a single CVE Record v5.2 from the MITRE CVE List by ID (e.g.No findings
Why it is in this group
- The name "get_cve_record" says "get": a word for reading.
Description, as the server wrote it 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.
get_epss_scoreGet the EPSS (Exploit Prediction Scoring System) probability for one CVE, sourced from FIRST.org.No findings
Why it is in this group
- The name "get_epss_score" says "get": a word for reading.
Description, as the server wrote it 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.
get_kev_catalogGet the CISA Known Exploited Vulnerabilities (KEV) catalog.No findings
Why it is in this group
- The name "get_kev_catalog" says "get": a word for reading.
Description, as the server wrote it 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.
get_modelsGet the model pricing and specs catalog across providers (Anthropic, OpenAI, Google, Meta, Mistral, Cohere, etc).No findings
Why it is in this group
- The name "get_models" says "get": a word for reading.
Description, as the server wrote it 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_news_articlesGet the latest AI news articles aggregated from 12+ sources (Anthropic, OpenAI, Google, HuggingFace, TechCrunch, The Verge, Hacker News, etc).No findings
Why it is in this group
- The name "get_news_articles" says "get": a word for reading.
Description, as the server wrote it 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.
get_osv_advisory_for_packageCross-ecosystem vulnerability advisory lookup via OSV.dev.No findings
Why it is in this group
- The name "get_osv_advisory_for_package" says "get": a word for reading.
Description, as the server wrote it 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.
get_research_papersGet recent AI/ML research papers from one of three feeds, chosen with the source argument.No findings
Why it is in this group
- The name "get_research_papers" says "get": a word for reading.
Description, as the server wrote it 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 Scholar across five fan-out queries, deduped, refreshed daily at 11:00 UTC. hf_daily is Hugging Face editor-curated with community upvotes and discussion counts, refreshed daily at 14:15 UTC. Pick arxiv_recent for what is brand new, trending for what is influential, hf_daily for what practitioners are discussing. License: arXiv and Semantic Scholar permit metadata use; the standard attribution block ships on every response.
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).Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_status_summary" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "chat": it reads messages.
- untrusted-inputThe description's first sentence says "get" and "chat": it reads messages, which other people can write.
Description, as the server wrote it 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 was last checked. Per-component detail is on /api/status.
search_sec_edgarLucene-style full-text search across the entire SEC EDGAR public-filings corpus since the 1990s.No findings
Why it is in this group
- The name "search_sec_edgar" says "search": a word for reading.
Description, as the server wrote it 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.
status_leaderboardCross-provider uptime leaderboard ranked by uptime % DESC, computed from minute-resolution counters (~720 samples per provider per day).No findings
Why it is in this group
- The name "status_leaderboard" says "status": a word for reading.
Description, as the server wrote it 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 the longer window. tier='full' uses the paid tier at any window. 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.
status_uptimeDaily uptime rollup for one provider over a window with operational/degraded/down day counts and uptime % (degraded counts as half-credit).No findings
Why it is in this group
- The name "status_uptime" says "status": a word for reading.
Description, as the server wrote it 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 paid tier at any window. 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.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
2 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__tensorfeed__register_free_watch"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:28 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 17
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 17 tools that change things (17 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.tensorfeed.ai/mcp: tools/list returned 30 tools to an anonymous client, including ask_tensorfeed (write), check_ai_supply_chain_risk (write), check_agent_reputation (write), submit_wantlist_item (write), register_free_watch (write) and 12 more
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 16 to 17
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 16 -> 17.View diff
- Tools that change things, listed without credentials: 16 to 17
Tools1 added, 1 removed.+1 added−1 removedView diff
- Added:ask_tensorfeedChanges things
- Removed:find_tensorfeed_data
Install
Pinned to version 2.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http tensorfeed https://mcp.tensorfeed.ai/mcpclaude mcp add --transport http tensorfeed https://mcp.tensorfeed.ai/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__tensorfeed__get_news_articles",
"mcp__tensorfeed__get_status_summary",
"mcp__tensorfeed__get_models",
"mcp__tensorfeed__get_cve_record",
"mcp__tensorfeed__get_kev_catalog",
"mcp__tensorfeed__get_epss_score",
"mcp__tensorfeed__get_osv_advisory_for_package",
"mcp__tensorfeed__search_sec_edgar",
"mcp__tensorfeed__get_research_papers",
"mcp__tensorfeed__get_agent_opportunities",
"mcp__tensorfeed__status_uptime",
"mcp__tensorfeed__status_leaderboard",
"mcp__tensorfeed__compare_models"
],
"ask": [
"mcp__tensorfeed__ask_tensorfeed",
"mcp__tensorfeed__check_ai_supply_chain_risk",
"mcp__tensorfeed__check_agent_reputation",
"mcp__tensorfeed__submit_wantlist_item",
"mcp__tensorfeed__register_free_watch",
"mcp__tensorfeed__route_verdict",
"mcp__tensorfeed__provider_reliability_verdict",
"mcp__tensorfeed__x402_settlement_verdict",
"mcp__tensorfeed__x402_publisher_verdict",
"mcp__tensorfeed__stack_safety_verdict",
"mcp__tensorfeed__benchmark_trust_verdict",
"mcp__tensorfeed__failover_verdict",
"mcp__tensorfeed__ssvc_verdict",
"mcp__tensorfeed__pricing_series",
"mcp__tensorfeed__benchmark_series",
"mcp__tensorfeed__whats_new",
"mcp__tensorfeed__provider_deepdive"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as tensorfeed. Review it before you use it.
Capability tags behind 3 rules
- mcp__tensorfeed__get_status_summary private-data, untrusted-input
- mcp__tensorfeed__register_free_watch outbound
- mcp__tensorfeed__get_agent_opportunities private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ai.tensorfeed/mcp-server/verify?hash=4f6088508797f6b763cfd9c8679d99e044715cb563c3625d33cdbae66b09bb80" | jq -e '.changed == false'Pinned hash 4f6088508797, from Nov 15, 2026, 23:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.tensorfeed/mcp-server/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.tensorfeed/mcp-server)Source: MCP Registry · repository. Synced Nov 15, 2026, 23:17 UTC.
TensorFeed MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the TensorFeed MCP server safe?
- No scan can promise that. What its definitions show: 30 tools, 17 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the TensorFeed MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the TensorFeed MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the TensorFeed MCP server have?
- 30 tools: 17 write, 13 read. ask_tensorfeed, check_ai_supply_chain_risk, check_agent_reputation, submit_wantlist_item, register_free_watch, route_verdict, provider_reliability_verdict, x402_settlement_verdict and 22 more.
Does the TensorFeed MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the TensorFeed MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): register_free_watch.
Has the TensorFeed MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.