"Multi-Agent Systems with Shared Memory Storage" matching MCP servers:

Enables macOS users to expose Lark/Feishu business tools to MCP clients such as Cursor and Codex, with stable semantic tools for reads and verified writes while preserving identity and policy safeguards.

Enables AI agents to access user and message data through MCP resources, providing REST API integration for user management with paginated lists and thread tracking.

Enables safe, multi-account Gmail and Microsoft 365 operations with explicit aliases, including searching, reading, drafting, archiving, labels/categories, and human-reviewed sending via a localhost approval window.

Gives MCP clients access to Google Workspace (Gmail, Drive, Calendar, Sheets, Docs, etc.) across multiple Google accounts simultaneously.

Local-first MCP server for agents that need to work across multiple Gmail and Microsoft 365 accounts without cloud token storage.

Persistent encrypted memory for AI agents. E2E encrypted private vaults, shared knowledge commons, topic channels, and agent-to-agent DMs. 23 MCP tools, free, no API key needed.

Connect multiple Gmail accounts to any MCP client, enabling search, read, draft, send, label, and organize mail across unlimited accounts with local-only OAuth token storage.

A Gmail MCP server with native multi-account support, enabling management of multiple Gmail accounts from a single server instance.

Lets Claude Desktop manage multiple Gmail accounts simultaneously, supporting search, read, send, reply, and label organization via MCP tools.

MCP server for Agent Room, enabling AI agents to join shared meeting rooms and collaborate with humans via tools like room_listen and room_task_*.

Enables an AI assistant to access and search across multiple Gmail inboxes simultaneously, allowing unified management of work, personal, and other email accounts through a single MCP server.

MCP server exposing multiple Google Workspace Gmail accounts to Claude, with support for verified send-as aliases and opt-in sending.

Lets Claude Code instances discover each other and exchange messages instantly across projects, with persistent peer IDs and automatic message rotation.

A local MCP server that provides shared, real-time context across multiple AI agents via WebSocket and MCP resource notifications, enabling collaborative workspaces, memory, tasks, and messaging.

An MCP server that provides read, label, and draft access to multiple Gmail accounts from a single server, never sending email.

Enables Claude and Codex sessions on the same host to communicate across different session systems via shared SQLite rooms, with named participants, durable ordered messages, offline delivery, and wait-based message handling.

Enables multi-agent collaboration across different AI assistants and projects by providing a universal coordination layer for MCP-compatible agents to communicate, share context, and coordinate complex tasks seamlessly.

Build production-grade multi-agent communication infrastructure in minutes. Real-time messaging, task scheduling, shared memory, and trust-based evolution — all via MCP + SSE.

MCP server that bridges multiple AI agents for unified local chat, supporting private messages, chat rooms, role queues, and broadcast with fixed identities and rate limiting.

agent-mq is a message queue that enables AI coding agents to communicate with each other across sessions and machines. Agents can send messages, delegate tasks, and coordinate work — all through MCP tools. Supports Claude Code, Cursor, Codex, OpenClaw, and any MCP-compatible tool. UUID-based authentication with per-user data isolation. Self-hostable with Docker.