Best Run AI Skills & MCP Servers
189 curated Run skills and MCP servers — install any of them into Claude, Cursor, ChatGPT, n8n, or any AI stack with one command.
Avito
Universal MCP server for the Avito API — 145 tools across 18 domains, safe-by-default with dry-run, idempotency, structured errors, MCP resources/prompts and cross-process token lock. Install via npx, plug into any MCP-compatible client.
Mcplab Reporting
HTML report generation for MCPLab evaluation runs
Aibvf
AI Value Trace and BVF, the agentic-native conversation framework. Run a Trace on a named account.
Blackwall
BLACK_WALL MCP server — a pre-action risk check your AI agent calls before any irreversible action (send email, move money, run SQL, delete data).
Ubon
Security scanner for AI-generated apps (Cursor, Lovable, Windsurf, v0). Catches hardcoded secrets, prompt injection, hallucinated imports, Server Actions / Edge runtime mistakes, and the vibe-coded vulnerabilities traditional linters miss.
Qiloback
QiloBack MCP server — orchestrate the QiloBack platform from any MCP-compatible AI client (Claude Desktop, Claude Code, Cursor, Windsurf, ChatGPT Desktop). Spawns the Python qiloback-mcp package; uvx is the recommended runtime.
Android Vitals
Android Vitals for AI agents: run npx android-vitals-mcp setup to connect your Play Console, then npx android-vitals-install-skills to get crash/ANR/rendering/startup playbooks in every AI CLI.
Server Code Runner
Code Runner MCP Server
Mcp
RunSec MCP server rewritten in TypeScript.
Server
MCP server for interacting with RunPod API
Grafana Npx
Grafana MCP server wrapper for running via npx
Server
MCP server for letsrunit — AI-agent browser test generation and execution
Faxdrop
Send real faxes from any MCP-enabled AI assistant. Wraps the FaxDrop API (PDF/DOCX/JPG/PNG, international numbers, status polling) with rate limits, dry-run mode, and audit logging.
Docs To
Convert any documentation URL into a ready-to-run MCP server — 100% local, no API keys needed
QueueSim
QueueSim is a free Model Context Protocol server that gives Claude — and any MCP-speaking AI — the ability to run real discrete event queueing simulations inside a conversation. Ask "I run a 3-agent call center, 30 calls/hr, 4-min handle time — what's my wait?" and get an actual
StratProof
StratProof runs honest backtests: real fees, real slippage, walk-forward validation. Six public tools, no OAuth. Call prove_strategy to test any strategy description ("Buy ETH when RSI(7) below 25, exit on 1.5% gain") and get a CONFIRMED / MIXED / DEBUNKED verdict with diagnosis.
Blockscout MCP Server
Provide AI agents and automation tools with contextual access to blockchain data including balances, tokens, NFTs, and contract metadata. Enable multi-chain support and deliver enhanced user experience with progress notifications for long-running queries. Facilitate seamless inte
Google Sheets
Read, write, and format spreadsheet data. Manage sheets, run formulas, and collaborate on structured data in real time.
Boar blockchain MCP (advanced)
Free, keyless MCP server with 50 read-only blockchain tools for Bitcoin, Ethereum, and Mezo. No installation, no API key required - just add the URL to your MCP client and start querying balances, transactions, blocks, ENS names, ERC-20 tokens, smart contracts, and more. Runs on
ClickHouse
Query ClickHouse Cloud — run SQL, list databases and tables, explore services and backups, inspect usage, run ClickPipes.
Go Process Inspector
Inspect and analyze running Go processes with detailed goroutine states, memory statistics, and binary information. Use an interactive terminal UI or HTTP API for programmatic access. Enable the MCP server to interact with Go process data via a Server-Sent Events endpoint and ava
About Run skills on iClaude
iClaude is the universal install layer for AI skills. Every Run skill on this page can be installed into Claude Code, Claude Desktop, Cursor, ChatGPT, n8n, Codex, and more — using a single copy-paste command. No config drift, no per-stack adapters, no manual MCP wiring.