TensorFeed MCP Server
Provides AI agents with real-time AI ecosystem data (news, status, pricing, latency) and premium tools paid via USDC on Base, compatible with any MCP client.
README
TensorFeed MCP Server
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 plus 14 premium tools paid 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?"
Why this exists
Most AI agents have a knowledge cutoff in the past. This MCP server gives them a window into:
- What's broken right now in the AI stack (Anthropic, OpenAI, Google, Mistral, others)
- What's new in the last 24 hours across 36+ news sources
- Current model pricing across every major provider
- Live AI bot traffic to a real production site (who's crawling, who's buying tokens)
- Smart model routing ("which model is best for THIS task right now")
- Cost projection before you commit to a workload
- Webhook watches that fire when a price changes or a service drops
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.
Free tools
No token required. Connect and use immediately.
| Tool | Description |
|---|---|
get_ai_news |
Latest AI news from 36+ sources, filterable by category |
get_ai_status |
Real-time status of Claude, OpenAI, Gemini, Mistral, and more |
is_service_down |
Check if a specific AI service is down |
get_model_pricing |
Compare pricing across all major AI model providers |
get_ai_today |
Summary of top AI stories from the last 24 hours |
get_agent_activity |
Live AI bot traffic on TensorFeed.ai with top-bot breakdown |
mcp_registry_snapshot |
Today's count + churn of the official MCP server registry |
probe_latest |
Last 24h of measured LLM endpoint latency per provider (TTFB / total p50/p95/p99). Measured, not self-reported |
Premium tools
Set TENSORFEED_TOKEN to enable. Tools are 1 credit each ($0.02 at base rate, less with volume bundles). Watches are also 1 credit at registration; reads/lists/deletes are free for the owning token.
| Tool | Description |
|---|---|
premium_routing |
Top-N ranked AI model recommendations for a task with full score breakdown |
pricing_series |
Daily price points for one model with min/max/delta summary |
benchmark_series |
Score evolution for a benchmark on one model |
status_uptime |
Daily uptime % for one provider with incident-day list |
premium_agents_directory |
Enriched agents catalog with live status, news, traffic, trending score |
news_search |
Full-text news search with date/provider/category filters and relevance scoring |
cost_projection |
Project workload cost across 1-10 AI models with 4 time horizons |
provider_deepdive |
One provider's full profile: status, models, pricing, benchmarks, news |
compare_models |
Side-by-side comparison of 2-5 models with normalized benchmarks |
whats_new |
Agent morning brief: pricing changes, incidents, top news from last 1-7 days |
mcp_registry_series |
Multi-day MCP registry growth and churn series, 90-day max range |
probe_series |
Daily SLA series for one LLM provider, 90-day max range |
create_price_watch |
Register a webhook watch on a model price change |
create_status_watch |
Register a webhook watch on a service status transition |
create_digest_watch |
Register a daily/weekly pricing-digest webhook |
list_watches, delete_watch, get_account_balance, get_account_usage |
Free token-scoped utilities |
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_..."
}
}
}
}
Setup with other MCP clients
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
# with premium tools enabled:
TENSORFEED_TOKEN=tf_live_... npx @tensorfeed/mcp-server
Example queries
Free tier:
- "What's happening in AI today?"
- "Is Claude down right now?"
- "Compare pricing between Claude Opus and GPT-4o"
- "What's the latency on Anthropic's API right now?"
- "Which AI bots are most active on the web today?"
Premium tier (with TENSORFEED_TOKEN set):
- "Recommend the cheapest AI model for code generation under $5 per million tokens"
- "Show the price history of Claude Opus 4.7 over the last 30 days"
- "What's Anthropic's uptime this month?"
- "Project monthly cost if we send 10M input + 2M output tokens/day to Claude Sonnet 4.6"
- "Set up a webhook to fire when GPT-5 pricing changes"
- "Give me a morning brief on what changed in AI in the last 24 hours"
Agent Fair-Trade Agreement
This server speaks AFTA. Every paid call:
- Returns no charge on 5xx, circuit breaker trip, schema validation failure, or stale data (older than the endpoint's published SLA)
- Returns an Ed25519-signed receipt your agent can verify against the public key at
tensorfeed.ai/.well-known/tensorfeed-receipt-key.json - Logs the no-charge event to a public ledger at
/api/payment/no-charge-stats - Honors a 100-call/min burn-rate breaker so a bug in your loop can't drain the wallet
The full standard is at tensorfeed.ai/agent-fair-trade. Manifest at /.well-known/agent-fair-trade.json.
Refunds, sanctions, terms
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.
Data source
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.
Star this repo
If this server is useful to you, a star helps other agent builders find it. Thank you.
Links
- TensorFeed.ai: https://tensorfeed.ai
- API reference: https://tensorfeed.ai/developers
- Premium / payments: https://tensorfeed.ai/developers/agent-payments
- AFTA standard: https://tensorfeed.ai/agent-fair-trade
- Hugging Face dataset: https://huggingface.co/datasets/tensorfeed/ai-ecosystem-daily
- npm package: https://www.npmjs.com/package/@tensorfeed/mcp-server
- Companion package, on-chain x402 verifier: https://www.npmjs.com/package/@tensorfeed/x402-base-mcp
- MCP registry: https://registry.modelcontextprotocol.io/v0/servers/ai.tensorfeed/mcp-server
- Sister site (real-time data dashboard): https://terminalfeed.io
- Issues / feature requests: https://github.com/RipperMercs/tensorfeed-mcp/issues
License
MIT. Built by TensorFeed.ai.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。