3818 Model Context Protocol servers — searchable, rated, ready to install.
OpenAI was the #1 lab on Arena for 95% of 2024. On 25 Sept 2026 it ranks 8th among labs, and.
Ledger of record for AI spend: verifiable receipts, waste auditor & model arbitrage MCP.
Find and redact personal data and secrets in text before it reaches a model. Local, no account.
Check a page's Meta, TikTok and OpenAI pixels, read reports and step-by-step fix guides.
Track competitors' Meta ads, save swipe files and run Meta campaigns from Claude, ChatGPT or Cursor.
Count and cut tokens in prompts, chats and agents for any model. Runs locally, collects no data.
Your Apple Health data, food diary and lifts, for ChatGPT, Claude and Gemini. Approved on iPhone.
Generate and edit GPT Image pictures with Ace Data Cloud; query the original image task.
Find retiring AI models and outdated API SDKs in your code, with dates, replacements and guides.
Hosted BigQuery MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Pixel-perfect Material (M3) data tables for your app in one prompt: Claude Code, Cursor, Codex.
Find retiring LLM calls in code and test the replacement model on real traffic before switching.
Live UK caravan, motorhome and campervan search, matching, dealer stock and model research.
Hosted Airtable MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Find open biology and chemistry AI models, bioinformatics tools and databases, and run them online.
Image and video generation with one Modelflare Smart API Key.
B2B or B2C, business category, and your own phrases, classified from a company's own website.
HVAC MCP server — fault codes, model lookup and answers cited to the OEM manual page.
Checks CLAUDE.md, AGENTS.md or a system prompt for 12 safeguards unattended agents need.
Google holds #1 in 6 of 8 Arena categories; Anthropic in 2. OpenAI has no category in the top.
12 image models (Nano Banana, GPT Image, FLUX…) and 10 tools in chat. No API keys. Pay per image.
Rankings, launches and featuring across the ChatGPT, Claude, Cursor and Grok Bot app stores.
Search, read and grow a Karpathy-style LLM wiki of linked Markdown pages, with cited answers.
qwen3.8-max trails claude-fable-5.1-max by 27 points. Over the past year the gap has stayed.
POST /mcp