2289 Model Context Protocol servers — searchable, rated, ready to install.
A decision model for the calls that don't have a right answer. The better option, with a reason.
Cloud, GPU and LLM token prices with index fixings. Pay per call over x402 or with a prepaid key.
Scans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks
Kalshi gold, silver, oil and crypto: live 15-minute markets, perps liquidation, and model edges.
Reference for multi-agent LLM topologies: patterns, aliases, sources, starters; one gated report.
Shared AI memory. ChatGPT, Claude, Cursor and any MCP app read and write the same memory.
Author, validate and maintain a CRAYON-C4 architecture model — never write an invalid file.
Free AI security tools: injection payloads, OWASP LLM mapper, ADLC release planner, test builder.
Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints
Judgment calls on small, cheap models: is this spam, which team, how urgent. YES, NO or UNSURE.
Suunto watch data (workouts, sleep, recovery, 24/7 activity) for Claude and other AI assistants.
OpenAI、Claude、Gemini 模型下架日、剩餘天數與官方建議替代，可檢查程式碼裡的模型。每筆附官方來源。
Genealogical research in the US National Archives Catalog: records, transcriptions, page images.
Let one coding-agent CLI consult another through Codex, Claude Code, OpenCode, or Antigravity.
Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)
Your YouTube library in Claude, ChatGPT and Cursor: transcripts, breakdowns, summaries, search.
Calibrated probabilities for Kalshi crypto, commodity and stock-index markets, plus a news wire.
Create, schedule and publish Instagram and Facebook posts from Claude or ChatGPT.
Ask Claude about your income and spending, and import bank statements. No bank login.
Simulate cloud architectures before provisioning. 9 free demo tools; an API key unlocks all 62.
Access Pollinations models and API capabilities through agent tools.
AI brand monitor: what ChatGPT and Claude say about your brand, press tracking, executive briefs.
Read your recorded AI agent runs, and what changed when you swapped a model or prompt.
Scans RAG content/scraped pages for indirect prompt injection
POST /mcp