Best Core AI Skills & MCP Servers

The agent eval standard for MCP. Score every agent output for quality, safety, and cost.

Continuous learning for Kiro agent sessions on AWS. Passive tool-use capture, LLM extraction, and synchronous context injection — inspired by claude-mem, aligned with Bedrock AgentCore Memory.

Org-wide persisted memory for AI coding agents via AWS Bedrock AgentCore. MCP server with short-term session events, long-term semantic search, and user/project/org namespaces.

Real-time web intelligence for AI agents. 21 tools, no required API keys. Every result timestamped with a freshness score.

Connect Claude Code to AgentsChat — AI Agent social network. Core tools stay lean while extended tool groups load on demand for lower token overhead and cleaner role-specific context.

L402 Lightning paywall + Depth-of-Identity score gate for MCP. Two integration shapes: (a) stdio MCP server exposing l402_gate_challenge / l402_gate_verify / l402_gate_score for agent clients; (b) drop-in Express middleware + MCP tool factory that combine

Search, compare, and analyze U.S. college data — costs, earnings, programs, and outcomes — via MCP. STDIO or Streamable HTTP.

Use the MCPSkills pre-install trust layer from Claude Code, Cursor, or any MCP client. Accepts GitHub repos, npm packages, Smithery URLs, and OpenClaw skills. 15 signals (incl. OSV/KEV/EPSS vulnerability intelligence), safety scanning, OpenClaw frontmatte

MCP server for GoldBean - 10 core paid APIs for AI Agents via x402 micropayments. Crypto price, weather, search, image-gen, code, AI chat and more. Pay-per-call with USDC on Base.

MCP server exposing PowForge Depth-of-Identity oracle to Claude Code, Cursor, and any MCP-compatible agent. Three tools: doi_score_lookup (priced via L402), doi_sign_vouch (unsigned-event builder), doi_score_verify (offline schnorr verification). The Ligh

MCP tool handler logic for the ggui protocol. Pure over @ggui-ai/mcp-server-core seams and consumed by @ggui-ai/mcp-server. Never imports AWS, HTTP transports, or CLI concerns.

VibeSpeed — Velocidade real do seu site. Core Web Vitals e PageSpeed via Google API em segundos.

MCP server validation CLI — fast pre-publish diagnostic for Model Context Protocol servers. Schema validation, tool/resource/prompt health checks, scorecard reporting, CI-ready exit codes.

Every AI skill, independently scanned. Coming soon. See https://github.com/OpenLatch/saferskills.

MCP server for EDIFACT CODECO, COPRAR, IFTSTA, COREOR — parse, validate against SMDG, reconcile cross-message, validate ISO 6346 check digits, decode size-type, look up SMDG code lists. Wraps @prefixcheck/edi inside the Model Context Protocol so any MCP c

Lightweight MCP server (Responses API core). OpenAI integration + web_search.

Lead Scoring Ai tools for AI agents. Capabilities: score lead, add lead, update lead activity. Built by MEOK AI Labs.

Find and filter RAG-capable MCP servers by meaning or keywords. Local stdio MCP bridge to the RAGMap subregistry (semantic search, filters, explainable scores).

MCP security trust layer. Scan packages, inspect repo MCP dependencies, generate Policy Gate setup, check exposure, and query abuse data.

Automatic MCP Server & OpenAI Tools Bridge for apcore

Core interfaces and reference storage adapters for the ggui MCP server — UiGenerator, SessionStore, BlueprintProvider, AuthAdapter, plus in-memory and SQLite implementations. The pluggable seam layer @ggui-ai/mcp-server is built on.

Core utilities for MCP servers built with ModelFetch

Search scientific papers from any MCP-compatible AI tool. Raw experimental data from full-text studies — methods, results, quality scores, and 25+ metadata fields per paper.

Recruitment Ai automation via MCP. Includes generate job description, score cv, generate interview questions. By MEOK AI Labs.