Best Run AI Skills & MCP Servers

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.

Local-first, LLM-agnostic memory layer for AI assistants. Run via npx @psraghuveer/memento.

Preste — sovereign agentic CLI with OODA/ReAct/Plan patterns, local MCP server for Claude Code/Desktop integration, and Ed25519 auto-attestation on every run. BYOK, standalone, no infra.

MCP server for AgentCall: phone numbers, SMS, OTP, AI voice (inbound + outbound) with 12 languages plus auto-detect, saved outbound agents per number (set/get/clear), retry-safe outbound calls via useSavedAgent + idempotencyKey for CSV runners, BYOK (brin

Claw Orchestrator — run Claude Code, Codex, Gemini, Cursor Agent, OpenCode and custom coding CLIs as one unified runtime. Drop into Hermes Agent, Claude Desktop, Cursor, Cline, Continue, Zed, Windsurf, Goose or any Model Context Protocol (MCP) host, insta

Create autonomous AI agents that actually execute tasks—read emails, manage git, run commands, search the web, and orchestrate workflows through natural conversation

CLI + MCP server for Fluxra — scrape comments, generate viral hooks, run AI research from the terminal or any MCP host (Claude Desktop / Code, Cursor, OpenClaw).

The shape-shifting MCP hub — shapeshift() into 130,000+ MCP servers at runtime. One entry point, no restarts, 7 registries.

GoPeak — MCP server for trusted Godot 4 workflows with compact/dynamic tool profiles, setup-gated LSP/DAP/runtime integrations, and migration-safe legacy compatibility.

Runtime feedback MCP server for AI coding agents. ViewGraph sees the UI - TracePulse feels the backend.

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

Voidly Pay SDK — agent-to-agent payments for AI agents. Sign envelopes, settle transfers, run x402 paywalls, verify webhooks.

Unified MCP server for multi-LLM consultation — registers tools from all available providers (Gemini, Codex, Ollama) behind runtime availability checks

Reduce Claude Code token usage by 70-90% with cross-session memory and four-layer optimization: semantic codebase indexing, PostToolUse tool compression, turn summarization, and session consolidation. MCP server powered by Ollama — zero API calls, runs en

MCP server for test runners — structured pass/fail results with failure details for AI agents

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.

MCP server that connects AI agents to LLM Conveyors — run Job Hunter, B2B Sales, and other AI agents from Claude, Cursor, or any MCP client

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.

Browser-based IDE + AI agent orchestration CLI. Run Claude Code in parallel across git worktrees, auto-approve safe tools with the Security Bouncer, and control long-running AI work from any device at app.mstro.app.

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.

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