Best Inference AI Skills & MCP Servers

MCP server for the OpenRouter management API — credits, inference-key CRUD with daily/weekly/monthly reset & expiration, activity drill-down (by_model/day/provider/key), one-shot dashboard.

Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles p

Outage radar for AI agents. LLM pricing, status, inference performance, and real-time agent-reported failure signals. 9 tools. No auth required.

Use your Claude Pro/Max subscription on your Obsidian vault. MCP connector that reads your markdown and proposes writes back, with all inference paid for by your existing subscription.

MCP server for SAM3 image segmentation, returning a pre-signed URL to inference results via stdio

MCP Server for HuggingFace inference endpoints with custom LoRA and story generation

Supply chain intelligence APIs for AI agents. Real-time freight rates (85+ carriers), crypto/forex/commodity prices, port congestion (NOAA), shipping lanes, economic indicators (FRED), and Cerebrix AI inference. 100 free calls/day, no signup. x402 USDC micropayments, ERC-8004 t

Real-time status, pricing, and inference latency for 90+ AI tools. Agent-reported failure signals with live fallback routing. No auth required.