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

Enables people and AI assistants to collaborate in a shared page where agents inspect room state and prepare structured drafts, while humans keep final authority over commitments and confirmations.

Enables simultaneous management of multiple Gmail accounts through MCP, allowing per-account reads and writes with verified labels and parallel search across all mailboxes.

Connects AI assistants to one or more Zoho Mail accounts, enabling read, send, search, reply, and delete operations directly from an AI workflow. Multiple mailboxes can run from a single lightweight process to reduce memory usage.

Agent Toolbelt is an MCP server exposing 11 focused API tools for LLM agents — schema generation, text extraction, token counting, CSV conversion, Markdown conversion, URL metadata, regex builder, cron expressions, address normalization, color palettes, and brand kits. Each tool is a focused microservice with structured input/output, WCAG-scored color data, USPS address parsing, and multi-model to

An MCP server that enables AI agents to instantly convert Markdown into beautiful, ready-to-deliver Word, PDF, HTML with sidebars, and Slideshow documents, bridging the "last mile" of AI content generation.

Enables AI assistants to manage MinIO object storage through comprehensive bucket operations, file uploads/downloads, batch processing, permissions management, and URL generation. Supports both automatic and manual connection modes with flexible authentication options.

An open-source MCP server that provides AI agents with secure access to read, search, and manage emails via Microsoft 365 and Gmail. It features security-first defaults like recipient allowlists and markdown content conversion to facilitate safe agent interaction with mailboxes.

Self-hosted football social-media agent that drafts posts, generates assets, and requires Telegram approval before publishing, with stateful SQLite storage and async image jobs.

Enables AI assistants to capture screenshots and control desktop input (mouse, keyboard) to see and interact with your screen. Features user-first safety controls including automatic pause on user activity and app allowlists to restrict interactions to approved applications only.

A webhook management and delivery service with MCP tools for endpoints, deliveries, relay, and incoming webhooks, enabling autonomous agents to send, track, and relay webhooks.

Sends desktop notifications when agents complete tasks, supporting local and remote agents.

MCP server for scheduling tasks with cron-like recurring jobs, one-time tasks, priority queues, retry logic, and job dependencies.

Enables MCP clients to chat with a single Watson Orchestrate agent by exposing invoke_agent and get_agent tools for sending messages and fetching agent details.

A Windows desktop automation MCP server that enables UI recognition through OCR, UIA controls, and multi-point color matching. It allows agents to interact with desktop applications via actions like clicking and typing while using a learning system to track and improve operation success.

MCP server for WeChat Mini Program debugging and automation, enabling agents to perform UI operations, screenshots, and regression testing through natural language commands.

Agent Droid Bridge gives AI agents programmatic control over Android devices and emulators via ADB, exposed as an MCP server.

Dynamic QR code platform for AI agents. Create, customize, and track QR codes without regenerating images. 37 tools covering 11 QR types (URL, vCard, WiFi, event…).

Enables Claude to interact with Jira, Salesforce, and n8n through MCP tools, allowing automated reading of Jira stories, deploying Salesforce metadata, and triggering n8n workflows.

A local MCP bridge that connects existing Codex and Claude Code conversations with DSH Web, enabling delegation, result retrieval, and human-in-the-loop coordination without leaving native chat apps.

An MCP server that lets an AI agent drive the iOS Simulator in a loop, enabling tapping, typing, swiping, reading the screen via the accessibility tree, and verifying app state.