3394 Model Context Protocol servers — searchable, rated, ready to install.
Prices, context windows, lifecycle and deprecation dates for 270+ AI/LLM models. Daily, no key.
Pay-per-call AI gateway: models, speech, web search, on-chain reads and NLP tools, via x402.
Amazon Seller Central and Ads in Claude or ChatGPT. Connect at agentxray.ai/connect.
Shared memory for AI tools: save once, recall word for word from Claude, ChatGPT, Codex or Gemini.
LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.
Generate and edit images with GPT Image 2.5 for $0.029 — free key, 50 credits, no card.
Uncensored image, image-to-video and chat generation for adult apps. OpenAI-compatible, pay per use.
86% of surveyed Claude users say AI makes them faster and 82% say it widens what they can do..
Independent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons.
Encrypted memory for Claude, on a server you deploy to your own Cloudflare account.
Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)
Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints
Daily AI-ecosystem data: GitHub AI/MCP repos, MCP registry, HF trending, LLM pricing, with history.
Cloud platform for asset research and investment allocation models, saving code, runs and outputs.
Compare LLM API prices, search models and providers, and access reviewed benchmark results.
Background sub-agents for Claude Code, Codex, Kimi and OpenCode, over MCP, with a spend cap.
Hands bulk reading to cheap OpenRouter models, masks secrets, checks each answer against the source
Model Context Protocol server for OpenText Software Delivery Platform.
Access Pollinations models and API capabilities through agent tools.
How often ChatGPT, Perplexity, Gemini and Claude mention and cite your brand vs competitors.
Compound Labs: eight keyless lookups. Model pricing, dep health, stack cost, registries.
Draft email campaigns in day3 from Claude Code, Cursor or VS Code as editable composer blocks.
Zero-model recall over your docs: the section that answers a question, in about a millisecond.
Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
POST /mcp