- Vibedonate @pooriaarab/vibedonateBitTorrent-style mesh for AI inference across agentic CLIs. Local-first.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Mingxin @mingxinstorage/mingxin-mcp-serverMeasured AI-inference-storage benchmarks with citations, article search, KV-cache ROI estimation.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- vLLM Ops @jaimenbell/vllm-ops-mcpRead-only ops/health MCP server for a local vLLM instance: health tiers, GPU/VRAM, service status.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Kirk — Unsupervised Structural Change Detection @ulyssesmodel/kirk-mcpThe Kalman filter for the non-Gaussian, non-stationary world. Unsupervised structural change.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Mendrift @suneel190700/mendrift-mcpMCP server for ML drift detection, MLflow registry diffing, and HMAC-gated model rollback5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Whetstone @cyberelf/toolsVerifier-grounded AI promotion gates, disposable report cards, and signed PASS/HOLD/BLOCK receipts.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- TrainTools @aparajeets/traintoolsRecommend paper-backed diagnostics for PyTorch and Hugging Face training problems.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- AI Guardian @aiops-tools/ai-guardianGoverned local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Inference AIops @aiops-tools/inference-aiopsGoverned GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- UnoRouter MCP @unorouter/mcpSearch 200+ UnoRouter models (most free), check pricing, and chat through one key5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Scorecard MCP @scorecard/mcpMCP server providing access to the Scorecard API to evaluate and optimize LLM systems.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- LLMTest @tjacquesson/llmtest-mcpBenchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Telegraph @telegraphprotocol/telegraphDecentralized AI inference (weather, deepfake detection, LLMs) with x402 USDC micropayments.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- ModelRunner @modelrunner/mcpRun 100+ AI models — image, video, audio, 3D — through one API with pay-per-use billing.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Hive Compute @srotzin/hive-mcp-computeHiveCompute MCP Server — decentralized inference router for AI agents10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- operant-mcp @saagpatel/operant-mcpRead-only MCP server for the OPERANT AI operating-agent calibration benchmark.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Qwen 2 @runapi-builder/qwen-2-mcpRunAPI MCP server for Qwen 2: create tasks, poll status, check pricing.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- ML Lab @rohithraju-ops/mcp-ml-labRun end-to-end ML experiments from natural language (XGBoost, LightGBM, Optuna).4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Qwen MCP @rocnubie/chat-mcpQwen AI Chat guide to Qwen3.6-Plus and qwen3.6-flash with practical notes on 1M context, coding7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- DeepSeek FR MCP @rocnubie/deepseekfr-mcpIndependent French workspace for evaluating DeepSeek-V3-class chat and DeepSeek-R1 reasoning.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Safe Kaggle MCP @parkseokjune/kaggle-mcpSafety-first Kaggle MCP — confirm-gated destructive ops, submission budget, injection-fenced.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- PathCourse Health (PCH) @pathcourse-health/mcp-serverCheaper LLM inference, USDC agent payments via x402, agent identity / reputation lookup.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Golden Dataset @nipunkhanderia/golden-dataset-mcpVersion-controlled golden datasets and RAG evaluation, no API key needed.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- MyAi @myaitoken/myai-mcpDecentralized AI inference on Base: OpenAI-compatible chat via community GPUs, paid in MYAI9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
