37 个#multi-agent MCP 服务器和客户端

Open Multi-Agent Canvas

CopilotKit

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

llm_to_mcp_integration_engine

Million19

The llm_to_mcp_integration_engine is a communication layer designed to enhance the reliability of interactions between LLMs and tools (like MCP servers or functions).

Share one memory store across all your AI coding tools. Memory Arbiter is a lightweight, fully local MCP Server with built-in dual-timeline conflict arbitration. No cloud, no LLM calls — just SQLite.

Open-source security audit framework covering all 10 OWASP Agentic AI threat categories (ASI01-ASI10). Scan multi-agent systems for prompt injection, data exfiltration, broken access control, and 7 more categories. Returns risk scores (0-100) with remediation priorities. Free tie

Nynch Mcp Server

peterod99

42-tool MCP server for CRM, relationship intelligence, and multi-agent orchestration. Search contacts, manage deals, analyze relationships, and coordinate AI agents.

Realtime shared context for AI agents and humans — live API specs, DB schemas, and versioned contracts so every agent and teammate works from the same source of truth across repos.

A neutral, attack-resistant reputation and trust layer for autonomous AI agents. Agent Guild lets an agent ask "who is the safest agent for this job?", vet any agent before delegating work or money, and vouch for completed work with cryptographically signed attestations. Reputati

Agent-to-agent knowledge exchange for trading intelligence. Agents publish empirical findings (sector failures, entry signals, exit patterns, regime signals), vote based on their own results, and earn reputation. Quality

A reusable AI software development team built on MCP. 13 specialized agents (Project Manager, Backend, Frontend, QA, Security, DevOps, UX, and more) collaborate via shared SQLite state. Exposes 44 MCP tools across 12 domains (projects, tasks, discussions, artifacts, decisions). O

Runtime security oracle for AI agents — scan prompts, tool calls, and outputs before execution. Pay-per-call via x402/USDC, no accounts needed.

Claude Octopus

xiaolai

One brain, many arms. Spawn multiple specialized Claude Code agents as MCP servers via the Agent SDK. Each instance gets its own model, tools, prompt, and personality.

A control plane for AI agents and human supervisors. Persistent task registry with scoped permissions, inter-agent delegation, and full provenance - all accessible via MCP.

Atomic gap-free id claims, advisory file leases, a shared event ledger + digest, presence, prose handoffs, and a task graph - so multiple agents (Claude Code, Cursor, Codex) stop colliding and re-deriving each other's work. Native Streamable HTTP, one claude mcp add. Open source

multi_agent

ankitrajkdnai

This is a Multi agent that utilizes MCP server to communicate and also Uses Azure Cloud Service

X402 A2a Hub

garyedgington

A discovery hub for AI agents navigating the x402 micropayment ecosystem. A single get_capabilities call returns the full service manifest — endpoint URLs, supported input/output formats, x402 payment details, and free trial endpoints for every live agent in the network. Use this

Ephemeral REST chatrooms where AI agents of different owners coordinate on a shared task. A room is one URL — no SDK, no registration. The owner creates a room, hands the URL to agents, and watches the conversation live in a browser. Remote MCP server at https://roomcomm.ru/mcp (

Ephemeral verification receipts for agent workflows. Agents create receipts to prove actions happened, then other agents verify before acting. Prevents duplicates, stale approvals, and unsafe retries. Receipts expire in 24 hours. Free API — sign up with the signup tool.

Competitive arena for AI agents via MCP. Register LLM or deterministic bots to compete in game-theory matches (Prisoner's Dilemma, Chess, Tic-Tac-Toe, Mafia, etc.) with ELO rankings, replays, and public leaderboards.

Persistent memory for AI agents. 72 MCP tools for remember, recall, rollback, audit,

Multi-agent shared brain across Claude Code/Desktop, Codex, Antigravity CLI (agy), Gemini, Copilot, and VS Code. One local SQLite store for threads, notes, verbatim quotes, and a dialectic user model; spawn/broadcast/whisper/inbox multi-agent coordination primitives; autonomous b

Existence Synchronization System Entity

VeniceEsse

MCP server that fuses 2–5 AI agents into one unified mind. Features 7 tools: esse_quick, esse_fuse, esse_execute, esse_list_agents, esse_list_sessions, esse_memory, esse_defuse. Supports Venice AI, OpenAI, and Anthropic. One AI. Many agents. Fused.

MCP Playground

skolte

Core MCP Server with React Frontend and Multi-Agent Support

The project tracker for teams of humans and AI agents — in plain files. MCP server + CLI, zero dependencies.

A nervous system for AI agents — awareness daemon, frame-based tool filtering, signal protocol, session handoff, and event triggers. 14 modules, 268 tests, zero dependencies. MCP server with stdio and SSE transports.

93 agentic MCP tools + 49 specialist agents for every major AI CLI. Self-learning, no API keys.

- 基于 AI 的智能搜索服务，支持多语言（简体中文、繁体中文、英文、日文、韩文、俄文、阿拉伯文）。

🧠 AutoGen-Compatible Multi-Agent Research POC with Ollama + BraveSearch

chin3

This project is a proof of concept for running a local-first multi-agent system using: 🤖 Local LLMs via Ollama 🧩 Simple function/tool-call detection using <tool_call>... 🔍 Brave Search API or optional Brave MCP plugin server 🧠 Two collaborating agents: Searcher and Synthesize

Attestor

bolnet

Audit-grade memory backbone for agent teams. Bi-temporal facts (event time + transaction time, with recall(as_of=...) replay), 6-step deterministic retrieval (no LLM in the critical path), conversation ingest with speaker-locked dual-pass extraction, per-tenant Postgres row-level

MCP-native agent-to-agent messaging hub for AI swarms. Agents communicate via channels and DMs through MCP protocol — zero SDKs needed. Includes web UI, semantic search, analytics dashboard. Single Go binary, local-first.

Context Capsule

Johnny-Z13

Portable context for agent workflows — structured handoff packets for AI agents

Shared control plane for AI coding agents — Claude Code, Cursor, Windsurf, and teammates sync tasks, persistent memory, decisions, and file locks through one MCP server. 12 consolidated tools (~15KB): task claim/release with resume packs, semantic memory search, lock policies & c

Nucleus Brain - Multi-Agent Orchestration

LKGargProjects

🧠 The Core of Your AI Agents

Multi-agent orchestration MCP server with atomic shared blackboard, FSM governance, per-agent budget enforcement, and adapters for 12 AI frameworks including LangChain, AutoGen, CrewAI, and OpenAI Assistants.

Codex Octopus

xiaolai

One brain, many arms. Spawn multiple specialized Codex agents as MCP servers via the OpenAI Codex SDK. Each instance gets its own model, sandbox, effort, and personality.