Best Run AI Skills & MCP Servers

Local encrypted vault MCP server. AES-256-GCM + Argon2id. Resolves {{PLACEHOLDER}} secrets at runtime so LLMs never see real API keys. Works with Claude Desktop, Cursor, Continue.dev, Cline, Open WebUI.

Quality checker for MCP servers — validates protocol handshake, discovery, tool-call dry-runs, and latency

Powerpipe MCP server to run benchmarks, detections and controls using AI.

Agent-first TikTok Content Posting API CLI and MCP server with dry-run publishing, OAuth readiness and privacy audit tools.

Durable, private, time-aware memory engine for long-running AI agents

Scaffold a Tap v2 browser-automation plan in seconds. `npx create-tap-script <site>/<name>` generates a deterministic .plan.json that runs at zero LLM tokens in Claude Code, Cursor, and any MCP host.

AI-native CI/CD that runs on your machine. Zero config, zero cost. Works inside AI agent sandboxes (Claude, Cursor, Windsurf). 33 languages, 40+ frameworks, 22 deploy targets, 25 installable skills, Tailscale mesh, blast radius analysis.

Convert Playwright scripts into Tap v2 plans. Compile .spec.ts / .test.ts files into deterministic v2 Plan JSON that runs at zero LLM tokens in Claude Code, Cursor, and any MCP host.

Dynamic MCP server toolkit for runtime toolset management with Fastify transport and meta-tools

Model Context Protocol (MCP) server for Cerebras Code API integration with any MCP-compatible client. Run 'cerebras-mcp --config' for setup or 'cerebras-mcp --remove' for cleanup.

MCP Hub is a local web UI for testing LLMs and MCP servers. Connect providers, inspect tool calls, and run multi-turn chats in one place.

Skar turns a captured AI agent trace into a committed pytest regression test. MCP server + CLI. Use when a tool-using agent run fails and you want to lock the failure as an executable test.

MCP server for csvtocsv.com — deterministic CSV transforms (Amazon→Shopify, Any-CSV→Amplitude cohort, CSV cleanup) usable from any agent runtime over stdio.

A2ABench MCP server for public agent Q&A benchmarking: list questions, submit runs, and fetch leaderboard scores.

Open-source CLI to minimize LLM token usage via smart code context extraction

MCP server for Deno — structured run, test, lint, and fmt output for AI agents

MCP server for Bun — structured run, test, build, and package data for AI agents

OpenCode plugin + MCP server + skill that runs an automated GitHub Copilot PR review loop: request review, wait deterministically via `gh run watch`, triage every comment, push fixes, reply, resolve, gated merge. Solves the silent-fail of github_request_c

Model Context Protocol (MCP) server for container runtimes (Podman and Docker)

Persistent sequential thinking MCP — chain-of-thought reasoning that survives sessions, resumes across agents, and saves conclusions as plan artifacts. Powered by ZeroDB. Zero-config: agents self-provision a ZeroDB account on first run, no signup required

Licium SDK — search resources, delegate to agents, run sandbox tests, connect to MCP servers dynamically

MCP server for Runframe incident management — any agent, any IDE, one system of record

Cloudflare runtime adapter for MCP servers built with ModelFetch

Scaffold a Voidly Pay-enabled AI agent in one command. Pick a template (paid MCP server, Hono x402 endpoint, FastAPI x402 endpoint, or zero-code universal proxy) and you're running in under 60 seconds.