3431 Model Context Protocol servers — searchable, rated, ready to install.
Read how often ChatGPT, Perplexity, Gemini and Google AI name your brand, its rivals and sources.
Publish HTML/code from your agent to openanthropic.com and get a shareable link.
Search an Obsidian vault by tag, term and wikilink graph. Read-only, deterministic, no embeddings.
Code review by AI models from different companies, usually two. Shows where they agree and disagree.
Order real 3D prints from chat: send an STL or OpenSCAD model, see one price, get it by UPS.
Stdio relay connecting Zed, Claude Desktop, Cursor and Codex to NV oOS WordPress MCP endpoints.
Web pages into decision-ready state: dates, numbers with units, budgeted chunks. No model, no key.
Give Claude, Cursor, or another AI assistant direct access to your QuickSnip library.
Every machine you have, for your agent: free GPUs, jobs, served models, software, over SSH.
Your own WhatsApp in Claude and ChatGPT: read chats, draft replies, send messages you approve.
Generates 1200x630 OG social preview images (PNG/SVG). Tools: generate_og_image, get_quota.
Kalshi 15-minute crypto markets, perps funding, liquidation math and bitcoin model edges.
OpenAI was the #1 lab on Arena for 95% of 2024. On 25 Sept 2026 it ranks 8th among labs, and.
Open weights briefly beat every proprietary model in early 2025 (deepseek-r1); today the best.
Since Jan 2024, Google's models have been #1 on Arena for 227 of 1003 days, third among labs.
claude-opus-4-6-high leads Arena coding at 1535. Anthropic has held #1 for 280 days, but Z.ai.
Multi-model debate with named dissent, plus decision provenance queries for AI coding work.
Commercially licensed image generation and editing with IP indemnification.
メールと LINE 公式アカウントの顧客対応サービス RenRaku を、Claude や ChatGPT などの AI から利用するための MCP サーバーです。
Read-only Duffer Golf facts: models and prices, room fit, FAQ, dealers and contact.
Crypto prices from Gemini. No key required.
Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model.
Plan AI video shots: model picks, sourced prompts, prompting guides and real $/s costs.
Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.
POST /mcp