Context7
ส่งคู่มือการใช้ไลบรารีและเฟรมเวิร์กรุ่นล่าสุดให้ AI อ่านก่อนตอบ ช่วยให้โค้ดที่ AI เขียนไม่ใช้คำสั่งเก่าที่เลิกใช้แล้ว
คำอธิบายจากผู้ทำ (ภาษาอังกฤษตามต้นฉบับ)
AI news, model pricing, service status, and machine-payable premium tools. AFTA-certified.
สามเรื่องนี้ไม่รวมเป็นคะแนนเดียว เพราะความเห็น การวัด และความนิยม เป็นคนละเรื่องกัน
ตัวนี้ยังไม่ได้เรียบเรียงเป็นภาษาไทย ด้านล่างคือข้อเท็จจริงที่เราอ่านจาก registry
เลือกโปรแกรม AI ที่คุณใช้ แล้วคัดลอกค่าตั้งไปวาง
TENSORFEED_TOKENค่าที่ติดป้ายความลับคือกุญแจของบัญชีคุณ อย่าส่งให้ใคร และอย่าวางในแชต
ต้องเตรียมก่อน
คุณใช้แอปไหน
เลือกแอปด้านบน เราจำไว้ให้ ครั้งหน้าปุ่มจะขึ้นว่า “ติดตั้งลง …”
ใช้ได้ทั้ง Claude บนเว็บ แอปคอมพิวเตอร์ และมือถือ:
https://mcp.tensorfeed.ai/mcpเปิด Claude Desktop → Settings → Developer → Edit Config แล้ววางค่านี้ในไฟล์ claude_desktop_config.json
{
"mcpServers": {
"tensorfeed": {
"command": "npx",
"args": [
"-y",
"@tensorfeed/mcp-server"
],
"env": {
"TENSORFEED_TOKEN": "ใส่ค่าของคุณ"
}
}
}
}พิมพ์คำสั่งนี้ใน Terminal
claude mcp add --transport http tensorfeed https://mcp.tensorfeed.ai/mcpclaude mcp add tensorfeed --env TENSORFEED_TOKEN='ใส่ค่าของคุณ' -- npx -y @tensorfeed/mcp-serverเติมค่าที่เว้นว่างไว้ก่อนรัน
วางในไฟล์ .cursor/mcp.json ของโปรเจกต์ หรือ ~/.cursor/mcp.json
{
"mcpServers": {
"tensorfeed": {
"url": "https://mcp.tensorfeed.ai/mcp"
}
}
}วางในไฟล์ .cursor/mcp.json ของโปรเจกต์ หรือ ~/.cursor/mcp.json
{
"mcpServers": {
"tensorfeed": {
"command": "npx",
"args": [
"-y",
"@tensorfeed/mcp-server"
],
"env": {
"TENSORFEED_TOKEN": "ใส่ค่าของคุณ"
}
}
}
}เบราว์เซอร์จะถามก่อนเปิดแอป จากนั้นแอปแสดงค่าตั้งให้ตรวจแล้วกดยืนยัน ช่อง key เว้นว่างไว้ให้คุณใส่เอง
วางในไฟล์ .vscode/mcp.json ของโปรเจกต์
{
"servers": {
"tensorfeed": {
"type": "http",
"url": "https://mcp.tensorfeed.ai/mcp"
}
}
}วางในไฟล์ .vscode/mcp.json ของโปรเจกต์
{
"servers": {
"tensorfeed": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@tensorfeed/mcp-server"
],
"env": {
"TENSORFEED_TOKEN": "ใส่ค่าของคุณ"
}
}
}
}เบราว์เซอร์จะถามก่อนเปิดแอป จากนั้นแอปแสดงค่าตั้งให้ตรวจแล้วกดยืนยัน ช่อง key เว้นว่างไว้ให้คุณใส่เอง
ChatGPT ต่อได้เฉพาะ server ที่อยู่บนอินเทอร์เน็ต:
https://mcp.tensorfeed.ai/mcpชื่อเมนูอาจต่างกันเล็กน้อยตามแพ็กเกจและรุ่นของแอป
ตัวเลือกเก็บในคุกกี้บนเครื่องนี้ ไม่ต้องมีบัญชี
ค่าตั้งนี้สร้างจากข้อมูลใน registry ของผู้ทำ ถ้าไม่ตรงกับ README ให้เชื่อ README
ชื่อและคำอธิบายเครื่องมือตามที่ server ตอบมาเมื่อ 7 พ.ย. 2569 ผู้ทำเป็นคนเขียน ไม่ใช่เรา แสดงเป็นข้อความล้วน
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 whet
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 publishedA
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 was
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_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.
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.
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.
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.
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", return
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), trust
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.
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 delive
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. Th
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 Scholar a
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, stars
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 fre
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 retry l
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 Base
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='previ
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: BLOCK
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 sco
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. Requires f
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 three
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 an X
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 wind
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 paid t
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 the
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 headline
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 (argum
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 wa
เราตรวจจากข้อมูลที่ใครก็เปิดดูได้ ยังไม่ได้อ่านโค้ด ข้อที่ไม่เกี่ยวกับตัวนี้ไม่นับในตัวหาร · ตรวจเมื่อ 7 พ.ย. 2569
ชื่อใน registry ยืนยันโดเมน tensorfeed.ai แล้ว (registry ตรวจความเป็นเจ้าของโดเมน)
ยังไม่ได้อ่านข้อมูล repo จาก GitHub
ยังไม่ได้อ่านข้อมูล repo จาก GitHub
ตอบกลับใน 100 ms (HTTP 200)
ไม่ต้องล็อกอิน
อ่านคำอธิบายเครื่องมือ 30 ตัวแล้ว ไม่พบคำสั่งแอบแฝงถึง AI
เทียบกับทุก server ที่ยังใช้งานในหมวดนี้ทั้งทะเบียน ดาวนับเฉพาะเมื่อผู้ลงทะเบียนเป็นเจ้าของ repo
จากการตรวจเบื้องต้นของเรา ผ่าน 3 จาก 3 ข้อที่ตรวจได้ เรายังไม่ได้อ่านโค้ด ก่อนใส่กุญแจหรือ token ให้ดูว่า server ขอสิทธิ์อะไร และเลือกกุญแจที่ทำได้เท่าที่จำเป็น
ต้องใส่ค่าเหล่านี้: TENSORFEED_TOKEN
ได้ทั้งสองแบบ จะลงในเครื่องหรือต่อผ่านคลาวด์ก็ได้
repo บน GitHub มีการแก้โค้ดล่าสุด – และส่งรุ่นล่าสุด (2.0.6) เข้า registry 8 วันที่ผ่านมา
โปรแกรมที่รองรับ MCP เช่น Claude Desktop, Claude Code, Cursor และ VS Code ตัวนี้ต่อผ่าน URL จึงใช้กับโปรแกรมที่รับ remote MCP ได้ เช่น ChatGPT ที่เปิดโหมดนักพัฒนา
ในหมวดเดียวกันมี Context7, Codebase Memory, Exa
server หมวดเดียวกันจากผู้ทำคนอื่น เรียงตามดาว
อ่านการ์ด:★ ดาว GitHubiสามเสา: รีวิว · ผลตรวจ · การใช้งานiอัปเดต = วันที่ส่งรุ่นล่าสุดเข้า registryi
ส่งคู่มือการใช้ไลบรารีและเฟรมเวิร์กรุ่นล่าสุดให้ AI อ่านก่อนตอบ ช่วยให้โค้ดที่ AI เขียนไม่ใช้คำสั่งเก่าที่เลิกใช้แล้ว
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
ส่วนนี้คัดจาก repo ของผู้ทำตามต้นฉบับ PopNx MCP ไม่ได้ตรวจหรือรับรองเนื้อหา ตัด HTML รูปภาพ และสคริปต์ออกแล้ว ลิงก์จะพาออกนอกเว็บ
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.
// claude_desktop_config.json
{ "mcpServers": { "tensorfeed": { "command": "npx", "args": ["-y", "@tensorfeed/mcp-server"] } } }
That's it. Restart Claude Desktop and ask: *"What's happening in AI today?"* or *"Is Claude down right now?"*
Most AI agents have a knowledge cutoff in the past. This MCP server gives them a window into:
The premium tools are paid per call in USDC on Base. No subscription, no signup, no API key emails. Buy a few credits, get a bearer token, agent uses it. The whole thing is Agent Fair-Trade Agreement certified: code-enforced no-charge on errors, breaker, schema-fail, and stale data; Ed25519-signed receipts on every paid call.
Prefer not to run a local process? The same TensorFeed data is served from a hosted Streamable HTTP MCP endpoint with a curated 33-tool subset (31 free + 2 premium), and its premium tools are payable per call with nothing but a funded USDC wallet: no account, no signup, no API key.
| Surface | URL |
|---|---|
| Canonical endpoint | https://mcp.tensorfeed.ai/mcp |
| Same endpoint, legacy path | https://tensorfeed.ai/api/mcp |
| Strict x402 transport (for auto-pay wrappers) | https://mcp.tensorfeed.ai/mcp?x402=strict |
// Any MCP client with an HTTP transport
{ "mcpServers": { "tensorfeed": { "type": "http", "url": "https://mcp.tensorfeed.ai/mcp" } } }
GET the endpoint for machine-readable discovery info. POST a JSON-RPC 2.0 envelope for initialize, tools/list, tools/call, and ping. The hosted catalog leans broader than this stdio package (SEC EDGAR full-text search, openFDA, EIA energy data, USGS earthquakes, NWS weather alerts, AI papers, agent-ecosystem scans).
Paying hosted premium tools with a wallet (x402): route_verdict (the signed model-routing decision) and whats_new (the full AFTA-signed morning brief) cost 1 credit ($0.02 in USDC, Base or Solana) per call. Call the tool unpaid to receive the canonical x402 payment requirements (the accepts array), sign, and retry with the base64 payload in the payment argument, or send it as an X-PAYMENT header. x402 auto-pay client wrappers should use the strict URL: unpaid premium calls there return a real HTTP 402 with a PAYMENT-REQUIRED header, and settled responses carry a PAYMENT-RESPONSE header plus the AFTA-signed receipt. Bearer credits tokens work on the hosted endpoint too. No USDC yet? Free trial credits via a wallet signature at https://tensorfeed.ai/api/payment/trial-credits.
No token required for the data tools; the three account utilities are free but scoped to your token.
| Tool | Description |
|---|---|
get_ai_news | Latest AI news from 15+ sources (Anthropic, OpenAI, Google, TechCrunch, arXiv, more) in one feed |
find_tensorfeed_data | Discovery tool: describe a data need in plain language, get the best matching TensorFeed endpoints |
get_ai_status | Real time operational status of major AI services (Claude, OpenAI, Gemini, Mistral, Cohere, more) |
is_service_down | Check whether one named AI service is operational, degraded, or down, with component detail |
get_model_pricing | Cross provider AI model pricing: input/output price per 1M tokens, context window, release date |
account_status | Your token's credit balance plus recent per endpoint usage (requires token, free) |
list_watches | List the active webhook watches owned by your token (requires token, free) |
delete_watch | Delete one of your webhook watches by id (requires token, free) |
The rest of TensorFeed's 100+ endpoints stay reachable through find_tensorfeed_data, which returns the matching endpoint URLs your agent can call over plain HTTP.
Set TENSORFEED_TOKEN to enable paid calls. Two pricing mechanics, both visible in each tool's own description:
tier parameter: tier="preview" (default) is free at 10 calls per IP per day, tier="full" costs 1 credit ($0.02) and adds the full ranking plus an AFTA-signed receipt.days parameter: days 1 to 7 are free, days 8 to 90 are paid.| Tool | Cost | Description |
|---|---|---|
route_verdict | Preview free, full 1 credit | Signed best fit model decision fusing pricing, benchmarks, usage, latency, and incident state |
provider_reliability_verdict | Preview free, full 1 credit | Signed ruling on the most dependable and riskiest AI provider from TensorFeed's own latency probes |
x402_settlement_verdict | Preview free, full 1 credit | Signed verdict on x402 USDC settlement market momentum and concentration on Base |
x402_publisher_verdict | Preview free, full 1 credit | Signed trust verdict on one x402 publisher domain's settlement activity |
stack_safety_verdict | Preview free, full 1 credit | Deploy gate (BLOCK/HOLD/PASS/UNKNOWN) for an AI software stack against CVEs and CISA KEV |
benchmark_trust_verdict | Preview free, full 1 credit | Signed ruling on whether an AI benchmark is still trustworthy or saturated/contaminated |
failover_verdict | Preview free, full 1 credit | Signed ruling on the best operational provider to fail over to when one is degraded |
ssvc_verdict | Preview free, full 1 credit | Signed SSVC patch urgency decision for one CVE using the CISA SSVC decision tree |
pricing_series | Days 1-7 free, 8-90 1 credit | Daily price points for one AI model over a window, with min/max/delta summary |
benchmark_series | Days 1-7 free, 8-90 1 credit | Daily benchmark scores for one model and benchmark over a window |
status_uptime | Days 1-7 free, 8-90 1 credit | Daily uptime rollup for one provider with operational/degraded/down day counts |
status_leaderboard | Days 1-7 free, 8-90 3 credits | Cross provider uptime leaderboard ranked by uptime percent, from minute resolution counters |
whats_new | 1 credit | Everything that changed in AI recently: pricing moves, new models, incidents, top news |
compare_models | 1 credit | Side by side pricing, benchmarks, status, and news for 2 to 5 models with rankings |
provider_deepdive | 3 credits, strict premium | Everything about one AI provider: status, every model priced and benchmarked, news, traffic |
create_watch | 1 credit at registration | Register a webhook watch for a price change, status transition, digest, or rank threshold |
Buy credits in USDC on Base at tensorfeed.ai/developers/agent-payments. Volume tiers: 10% off at $5, 25% off at $30, 40% off at $200. First payment from a new wallet gets a 50-credit welcome bonus.
// claude_desktop_config.json — premium config
{ "mcpServers": { "tensorfeed": { "command": "npx", "args": ["-y", "@tensorfeed/mcp-server"], "env": { "TENSORFEED_TOKEN": "tf_live_..." } } } }
The same command + args + env block works in Claude Code, Cursor, Continue, Cline, Zed, and Goose. Anywhere that takes a stdio MCP server config, this drops in.
Run standalone for testing:
npx @tensorfeed/mcp-server
TENSORFEED_TOKEN=tf_live_... npx @tensorfeed/mcp-server
Free tier:
Premium tier (with TENSORFEED_TOKEN set):
This server speaks AFTA. Every paid call:
tensorfeed.ai/.well-known/tensorfeed-receipt-key.json/api/payment/no-charge-statsThe full standard is at tensorfeed.ai/agent-fair-trade. Manifest at /.well-known/agent-fair-trade.json.
All credit purchases are final per Section 17.5 of the Terms. Credits do not expire and are jointly redeemable on tensorfeed.ai and terminalfeed.io, so the safe pattern is to buy small ($1 USDC for 50 credits) and top up as call volume is calibrated. Premium access is unavailable in OFAC-sanctioned jurisdictions per Section 17.9.
All data comes from the TensorFeed.ai API, which aggregates 42 feeds across the AI ecosystem (news, pricing, benchmarks, status, GPU pricing, MCP registry growth, latency probes, agent traffic, AFTA adopters, training datasets, embodied AI, hardware, and more). A daily JSONL snapshot of the full corpus is published to Hugging Face at tensorfeed/ai-ecosystem-daily under an inference-only license.
If this server is useful to you, a star helps other agent builders find it. Thank you.
ตัดมาแค่ช่วงต้น อ่านต่อใน repo