"Two agents working simultaneously" matching MCP servers:

Provides local persistent working memory for AI agents, allowing them to load rules, preferences, and project state before tasks and save validated experiences after successful completion. Works with stdio MCP clients via a local JSON file.

A deterministic Mastermind-style cipher lock exposed as MCP tools for benchmarking LLM reasoning and tool-use through a legible duel.

Prevents context bloat and the 'Lost in the Middle' phenomenon by distilling action histories into concise summaries while maintaining a clear core objective.

Enables AI assistants to delegate specific tasks to specialized sub-agents (e.g., test-writer, code-reviewer). Supports both Cursor and Claude Code with custom agent definitions.

Enables an AI agent to launch, monitor, and steer multiple coding agents running in tmux panes, including sending keystrokes, waiting for idle or output patterns, and managing sessions.

Enables local deterministic discovery, validation, and selection of validated skills through MCP tools, producing consistent plans without executing any skill.

Enables orchestrating multiple specialist Claude Code agents as a team, with live visualization and agent-to-agent messaging.

nexus-agents makes your AI coding tools work together intelligently. It coordinates Claude, Codex, Gemini, and OpenCode — routing each task to the best model using data-driven algorithms, validating outputs through multi-model consensus voting, and continuously improving through outcome-driven learning. Connect it to any MCP-compatible editor (Claude Code, Cursor, VS Code) and it handles the rest.

Enables running AI agents via OpenAI-compatible APIs with custom system prompts, models, and queries. Supports persistent memory, preset agents, and multi-step workflows like pipelines and swarms.

The simplest way to bridge and collaborate across AI Agent sessions like Claude Code, Codex, Gemini, or Cursor. It allows your agents to combine their strengths to solve your most difficult tasks without leaving their current context.

Enables running isolated main and sub agent tasks in networkless Docker capsules with explicit input grants, verified artifact delivery, and independent reviewer oversight via MCP tools.

MCP server that enables AI agents to autonomously buy virtual phone numbers and receive SMS verification codes. Supports multiple providers (5sim, SMS-Activate, OnlineSim) with automatic cheapest-provider selection.

Enhances Claude Code's Task tool with session resumption and independent agent execution, allowing autonomous subagents from .claude/agents/ with true parallel batch support.

Enables multiple AI agents using MCP-compatible clients to collaborate in parallel on the same project across one or more machines, with direct messaging, a shared task board, atomic file/folder locking, presence tracking, and a live web dashboard.

Enables listing, inspecting, chatting with, and waking deployed Voight Agents from any MCP client, including checking agent state, usage, tasks, and GPU status.

Enables coding agents to publish and read events on channels, notify humans, and ask yes/no, multiple-choice, or free-text questions, returning answers as tool results.

Enables one coding agent to inspect, configure, debug, and repair another agent over stdio MCP, with redacted reads and confirm-gated writes and restarts.

Enables two local LLMs (Qwen and Llama) to communicate via MCP, allowing one model to consult the other for second opinions or additional reasoning.

Enables declarative agent manifest management and deterministic brief validation for the Presentador→Orquestador flow, with tools to list/get manifests and validate brief schemas.

Enables AI assistants and other MCP clients to launch and steer Cursor Cloud Agents on repositories or as repo-less research tasks, including model selection, mid-run follow-ups, cancellation, result retrieval, and run listing. Also exposes authentication checks and per-agent or per-run token usage and cost reporting.