Best Runtime AI Skills & MCP Servers

AWS Lambda runtime adapter for MCP servers built with ModelFetch

Supabase runtime adapter for MCP servers built with ModelFetch

TRACE32 CMM language server via MCP — parse, diagnostics, completions, hover, symbols, and CLI validation for PRACTICE scripts. Native binary, no Node.js runtime needed.

Next.js runtime adapter for MCP servers built with ModelFetch

TypeScript runtime and CLI for connecting to configured Model Context Protocol servers.

Scoped Bilig WorkPaper runtime and MCP server for Node.js services, agent tools, and server-side spreadsheet formulas.

Plugin-based MCP server for React Native/Expo runtime debugging, inspection, and automation via Metro/CDP

Sprigr MCP server — local AI agent search with WASM-powered full-text search and hybrid semantic search. Also exports a Workers-compatible runtime for in-process search inside Cloudflare Workers / bundled environments.

Shared MCP server building blocks for @us-all servers — token-efficient by design (category toggles, extractFields, search-tools meta, registry, runtime)

Hud MCP

AI-native web browser runtime for autonomous agents with human supervision

Gnosys — Persistent Memory for AI Agents. Sandbox-first runtime, central SQLite brain, federated search, Dream Mode, Web Knowledge Base, Obsidian export.

The runtime behind FocusMCP — Registry + EventBus + Router composing MCP bricks on demand. Browser-compatible, zero-dep, TypeScript strict.

Model Context Protocol server exposing the b402 Solana SDK as agent-callable tools (Claude Code, Cursor, any MCP runtime)

Runtime, compiler, lint, CLI, and dashboard for Skillscript — a small declarative language for authoring agent workflows.

Conformance test runner for FocusMCP bricks — validates manifests, tool schemas, and runtime behavior.

SkillFM local — single npm package for the SkillFM platform on user nodes. Subcommand router exposes (1) Beacon MCP stdio server (cost-optimizer for any agent; merged in from @skillfm/beacon-mcp on 2026-05-01), (2) skill runtime (BYOK Playwright / brain r

Core runtime library for Caplets progressive disclosure gateways.

Skilder Runtime - NodeJS processes for edge execution connected to backend orchestrator via NATS

MIT-licensed MCP bridge to the Alethia runtime — the patent-pending zero-IPC E2E test runtime for AI agents. 2-5x faster than Playwright MCP. Signed evidence packs, EA1 fail-closed safety gate, WCAG + NIST 800-53 audits built in. Local-first, zero telemet

Production-grade WordPress operations toolkit for AI coding agents — default-safe wp-cli + REST + scoped fs, opt-in companion for execute-php + runtime introspection. MIT, rolepod ecosystem.

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

VibeCheck MCP — the code intelligence layer for AI-built software, wired into your agent. Truth-grounded, runtime-aware, multi-agent. 16+ verification engines, runtime probes, and live truthpack context for Cursor, Claude, Windsurf, and any MCP-compatible

Provider-neutral agent runtime for coding workflows. Verified DAG execution with evidence gates, worktree isolation, and local graph memory.