3748 Model Context Protocol servers — searchable, rated, ready to install.
Scans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks
Local-first PHI detection for source code, LLM prompts, logs, and analytics
Verbatim transcription of public video/audio URLs to clean text, SRT, and timestamped records.
Claude 나 Codex 에서 벨로그(velog.io) 글을 읽고 쓰고 백업한다. 다이어그램과 시퀀스도 그린다. 공개 발행은 사람이 켤 때만 열린다.
Connect MCP clients to 2,000+ AI models without managing provider API keys.
Generate reproducible image, video, and audio assets with leading models and your own provider keys.
New AI models on HuggingFace: releases, weights. Be born in one call — free testnet funds.
Your family office in Claude, ChatGPT, Codex and Muse: trusts, entities, documents, cited.
Ask Claude or ChatGPT about your own crypto trading: performance, patterns and behaviour.
Send WhatsApp messages from Claude. No Meta Business approval or WhatsApp Business account.
Persistent, outcome-grounded episodic memory for Claude. 14ms CPU retrieval, no GPU, no vector DB.
BridgeNode — x402 pay-per-request AI inference. OpenAI-compatible API + MCP, Solana USDC, gas-free.
AI-native Kanban board — connect Claude to claim, work and move your tasks over MCP.
Deploy autonomous LLM trading agents and drive them over MCP.
Single-binary local RAG MCP server in Rust. MiniLM compiled in, hybrid search, zero deps.
Local, cross-provider preflight checks for LLM integration changes.
Financial Modeling Prep API as MCP tools — quotes, statements, prices, and ~240 endpoints.
Generate AI images and videos from any compatible MCP client.
Records your Claude Code, Codex and Pi history before deletion. Cited-or-abstain recall.
User-approved phone calls, speech, transcription and voice agents with PyAI OAuth.
Public read-only discovery of agent, model, training, task, and verification opportunities.
Trust gate for AI agents: multi-model adversarial consensus, signed and verifiable verdicts.
Local, privacy-preserving PII toolkit over MCP — shape to the model, substance stays local.
Local 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.
POST /mcp