Best Layer AI Skills & MCP Servers

ASG Agent Pay — the banking layer for autonomous AI agents. Multi-chain payments (x402 + MPP), virtual cards, policy engine, and wallet abstraction across 17 networks. The only SDK unifying Coinbase x402 and Stripe MPP protocols.

MCP server for the Agent Passport System — protocol-layer tools only. 150 tools (132 protocol + 10 gateway deprecation stubs). Identity, delegation, reputation, attestation, coordination, commerce, attribution primitive, attribution settlement. Tracks SDK

XLUXX Trust Layer MCP Server — 16 tools for runtime trust scoring of 15,000+ MCP servers, Resonance Engine analysis, and Context Gate integrity checks. Installable in Claude Desktop, Cursor, and any MCP-compatible host.

Behavioral governance layer for LLMs - monitors for hallucination, inconsistency, tone drift, and unsafe reasoning while managing stateful AI sessions

Intlayer MCP server. Handle MCP to help IDE to use Intlayer. It build, fill, pull, push, dictionaries

Apple-native execution layer for AI coding agents: compile, validate, repair, and prove Swift surfaces.

DEPRECATED — install the Claude Code plugin at gramatr/claude-plugin instead. This npm package no longer ships a CLI; Codex and Gemini integrations are paused pending HTTPS+OAuth MCP support.

Mneme — the memory layer for your codebase. Knows the WHY, the WHAT, the WHERE-IT-BREAKS.

Payment layer for AI agents. One MCP, five protocols, thousands of paid APIs your agent can call.

Local-first MCP memory server for operational project state: decisions, blockers, plans, patterns, and next moves. The persistent memory layer that stops agent amnesia.

Create a Context Hub — a personal AI context layer shared across any MCP client (Claude.ai, Claude Code, Claude App, ChatGPT, Perplexity, Cursor, and more). One command to scaffold, deploy, and connect.

On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.

Local memory layer for AI agents — coding assistants over MCP, game NPCs over REST

Security, cost, and health governance proxy for MCP infrastructure — three-layer detection engine (regex + schema + LLM), monorepo, corpus, CI/CD

MIND MCP Server — 28 tools. The most complete AI memory layer with the Focus → Project → Outcome → Task hierarchy (mind_focuses + extended mind_life with item_type/parent_id/focus_id and cross-account project sharing via share/list_shares/revoke_share), d

Open-source cross-agent memory layer for coding agents across Cursor, Claude Code, Codex, Windsurf, Gemini CLI, Copilot, Kiro, OpenCode, Antigravity, and Trae via MCP.

HITL infrastructure for AI agents. Your agent calls awaitHuman(), a human reviews via Slack/email/dashboard, agent resumes with a typed response.

Secure MCP server for web browsing with multi-layer fetcher chain - no API keys required

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

CodeLoop MCP server - verification, self-repair, and recommendation layer for AI coding agents

The CLI for IronBee — Verification and Intelligence Layer for Agentic Development

Hashlock Markets — atomic settlement layer for the agent economy. Sealed-bid RFQ + HTLC atomic settlement, fused into one operation. Live on Ethereum and Sui mainnets; Bitcoin HTLC mainnet-ready via P2WSH scripts (no contract to deploy; signet-validated);

Orchestration + observability + coach layer for Claude Code token optimization. Measures tool usage, enforces budgets, advises on complementary tools (serena, RTK), and proactively surfaces savings tips.

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