Best Shared AI Skills & MCP Servers

Shared utilities for Pare MCP servers

Shared, persistent memory for AI assistants, built on the Zettelkasten method.

Shared core infrastructure for the Brain ecosystem — IPC, MCP, CLI, DB connection, and utilities

Shared utilities and server orchestration for building MCP (Model Context Protocol) servers

MCP server for Prior — the knowledge exchange for AI agents. Search, contribute, and improve shared solutions.

Bhived MCP Server — shared knowledge graph for AI agents. Query, write, and inspect collective AI knowledge through the Model Context Protocol.

Shared TypeScript types and x402 payment-flow utilities for @xenarch/agent-mcp — Xenarch's non-custodial x402 MCP server.

MCP server for Google Drive, Google Docs, Google Sheets, and Google Slides with full read/write operations, rich markdown-to-docs formatting, theming, shared drive support, and OAuth2 authentication

Ephemeral shared workspace for AI agents - cache contexts, bridge multi-agent workflows, and share data between sessions. Free 2-hour temporary storage.

Shared utilities for @atlassian-dc-mcp MCP servers. Not affiliated with Atlassian.

Shared authentication library for F5 Distributed Cloud MCP servers - XDG-compliant profile management

Google Drive MCP server with Google Workspace awareness — Docs, Sheets, Slides, Shared Drives, Labels, Approvals, and domain-wide delegation support

DARE Framework - CLI, GraphRAG engine, MCP server and shared types in a single package

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

Connect Claude Code sessions across projects via shared context bundles

Shared utilities for Paparats MCP - path validation, gitignore filtering, language-aware exclude patterns

Shared state for multi-agent — share context, files, results between agents, broadcast messages.

Shared type definitions for Undisk MCP — storage, tools, and protocol types

Unified AI coding agent with MCP integration for Claude, VS Code, and Kiro IDE. Features persistent knowledge graph via OverdriveDB, token compression (60-80%), multi-model switching, and shared/independent project modes.

Shared Zod schemas and TypeScript types for the mpak registry

MCP server for LaunchRoad — gives any MCP-compatible AI coding assistant (Claude Code, Cursor, VS Code, ChatGPT Desktop) live read/write access to your team's shared brain.

Extended Google Drive MCP server via gogcli — auth + full Drive support (upload/download/permissions/comments/shared drives)

MCP server for SharedMemory — persistent AI memory for any tool

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.