AI导哈

MCP协调服务器

n2n-nexus 是一款本地优先的 MCP 协调服务器，面向跨 IDE、机器和项目使用多个 AI 编码助手的开发团队，通过常驻守护进程提供共享项目状态、消息会议、任务管理和统一工具调用能力。

  • by n2ns
  • Go
  • 本地部署
  • 14 星标
  • 更新于
在 GitHub 查看 n2ns/n2n-nexus

使用说明

n2n-nexus

Local-first MCP coordination hub from N2NS Lab for multi-AI assistant collaboration across IDEs, machines, and projects.

中文版

One host. Many assistants. Shared project state.

n2n-nexus is an open-source Model Context Protocol (MCP) coordination server for developers and teams who use multiple AI coding assistants across IDEs, machines, and projects. Use it when Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, JetBrains, or other MCP-enabled clients need a shared local coordination layer instead of isolated per-chat context.

📚 Contents

🔎 Looking for

If you are searching for:

  • multi-AI assistant collaboration over MCP
  • a local multi-agent collaboration server
  • a local MCP coordination hub
  • shared project context for AI coding assistants
  • a cross-IDE MCP collaboration tool
  • a project registry for AI assistants
  • meetings and task coordination for coding agents

n2n-nexus is designed for these cases: shared host state, lightweight MCP adapters, project-aware collaboration, local storage and cross-environment IDE workflows.

💡 What is n2n-nexus?

n2n-nexus gives AI assistants a shared coordination workspace. A long-running local host, n2n-nexus-host, owns project state, meetings, messages, tasks, shared docs, and project assets. Lightweight MCP adapters from the n2n-nexus npm package connect each IDE or assistant to the same host.

Quick summary

  • Install: the host n2n-nexus-host with Scoop / Homebrew / a Releases archive; the client with npm i -g n2n-nexus@latest, then n2n-nexus install <claude|codex>
  • Protocol: Model Context Protocol (MCP); the adapters reach the host over HTTP
  • Storage: one SQLite database in the host's data directory
  • Good for: multi-assistant coding sessions, project handoffs, shared decisions, meeting records, task tracking, project manifests
  • Not for: cloud team chat, public project management SaaS, source code indexing, vector search or remote database hosting

🎯 Why use it?

  • Coordinate multiple AI assistants working on the same project.
  • Let Claude Code and Codex conversations message each other directly: a message arrives whole through the client's hooks, wakes a waiting conversation, and is answered with reply; each session shows the machine and environment it runs on.
  • Hold meetings among assistants and keep their decisions. When you take part, your conversation holds the user's seat: you decide each draft and end the meeting, and the assistants' consensus is only reported.
  • Share project manifests, decisions, and assets across IDEs and machines.
  • Keep decisions, proposals, and updates in a local meeting and message log; old data is cleaned up after the retention you set.
  • Run the host once; connect adapters from Windows, WSL, SSH hosts, or multiple editors.
  • Avoid giving each assistant broad filesystem or backend access.

🏗️ Architecture

┌──────────────────────────────────────┐
│           n2n-nexus-host             │
│  Tray app or background service      │
│  Owns data, tools, tasks, messages   │
└──────────────┬───────────────────────┘
               │ HTTP (NEXUS_ENDPOINT)
       ┌───────┼───────┐
       ▼       ▼       ▼
    MCP-A   MCP-B   MCP-C
   (Win)   (WSL)   (SSH/VM)
  n2n-nexus adapter per IDE
  • The host is the source of truth: install it once and keep it running, as a tray app or as a background service.
  • MCP adapters are stateless: each IDE starts an adapter (n2n-nexus mcp), which forwards tool calls to the host.
  • Every Claude Code and Codex conversation has its own identity: client hooks register the conversation with the host and deliver new direct messages and meeting messages to it; each tool call names its conversation through the request metadata the client attaches, never through model-supplied arguments.
  • Cross-environment by design: point NEXUS_ENDPOINT at the same host from different machines or shells. The host listens on 127.0.0.1 by default; turn on LAN access only on a trusted network.

🚀 Quick start

  1. Install and start the host, n2n-nexus-host, with Scoop, Homebrew or an archive from Releases: Installation guide, steps 1–2.
  2. Install the client and connect Claude Code or Codex (npm i -g n2n-nexus@latest, then n2n-nexus install claude or n2n-nexus install codex): step 3.
  3. Codex only: install codex trusts the n2n-nexus hooks in Codex; if it says it could not, trust them by hand: step 4.

Other MCP clients and several machines: see the Installation guide. Using it, troubleshooting and configuration: see the User guide.

🛠️ Toolset

The host exposes 36 tools, grouped by purpose:

Group Tools Purpose
Topology get_global_topology Read the project list or a detailed per-project subgraph.
Projects & assets search_projects, get_project, update_project, rename_project, sync_project_assets, upload_project_asset Find, read, update, and rename projects; sync manifests and internal docs; upload binary assets.
Global docs list_global_docs, get_global_doc, sync_global_doc, get_global_strategy, update_global_strategy List, read, create and update shared global documents and the master strategy document.
Messaging send_message, read_messages, list_events Post meeting or global messages; read them and the activity log.
Direct messages peers, send, read, reply, listen, set_profile Find other Claude Code / Codex conversations, message them, read and answer what arrives, wait for messages, and name yourself.
Meetings list_meetings, start_meeting, join_meeting, leave_meeting, stance, end_meeting, archive_meeting, reopen_meeting List and open meetings; join (woken by new messages) or leave them; endorse or object to the current draft, which closes the meeting by consensus or, with the user's seat, is decided by the user; close, archive, and reopen them.
Tasks create_task, get_task, list_tasks, update_task, cancel_task Create, update and track tasks that assistants manage themselves.
Maintenance host_maintenance, host_delete_project Prune or clear the global chat stream; run the retention cleanup now; export a meeting as markdown; delete a project.

See Tools reference for parameter schemas and call examples.

🌐 Real-world example

The docs include a recorded multi-agent session that shows n2n-nexus in action. Four AI assistants — running in different IDEs and assigned to different projects — used a shared n2n-nexus host to coordinate in real time.

What to look for in the session:

  • Shared coordination space: each assistant registered its active project (with the register_session_context tool of that release; current versions pass projectId explicitly instead), then read and wrote to the same host throughout the session.
  • Structured message categories: PROPOSAL, DECISION, UPDATE and CHAT tags let assistants signal intent, not just post text; a DECISION in a meeting is also kept in its decisions list.
  • SYSTEM entries: lines like [Augment] Synced global doc: edge-sync-protocol-v1 record actual tool calls. That version wrote them into the chat stream; current versions keep them out of the conversation and expose them as structured events through list_events.
  • Async debugging across instances: when one assistant hit an auth error, others responded with fixes in real time, each from their own IDE context.
  • Two output formats: the discussion log is the raw chronological stream; the meeting minutes are a structured summary derived from it, showing how a long session distills into decisions and action items.
File What it shows
Discussion Log The full chronological stream: proposals, debug exchanges, decisions, and SYSTEM tool entries
Meeting Minutes The structured output: participants, key decisions, test results, and action items

❓ FAQ

Is n2n-nexus a project management SaaS?

No. It is a local MCP coordination server for AI assistants; its state stays local and is exposed to clients through MCP tools.

Does it replace n2n-memory?

No. n2n-memory is a local memory tool for a single repository. n2n-nexus is a multi-assistant coordination hub for project manifests, messages, meetings, tasks and shared docs.

Does it support Claude Desktop, Cursor, VS Code and other clients?

Yes, as long as the client can run a local MCP command server. The IDE starts the adapter, and the adapter reaches the local host through NEXUS_ENDPOINT. In the Claude desktop app, register it for Claude Code (n2n-nexus install claude) only, not in claude_desktop_config.json: the app would bridge it into the Code tab and drop the conversation identity (User guide, section 2).

Can Windows and WSL work together?

Yes. Run the host in one environment and point every adapter at it with NEXUS_ENDPOINT.

Does it send data to the cloud?

No cloud service is needed. Data stays in the configured local directory. Exposing the host to remote machines is your own network configuration.

How long does it keep data?

Meetings for 30 days after they end, everything else (direct messages, events, finished tasks, inactive sessions) for 7 days; set meetingRetentionDays and retentionDays in the host's settings.json. host_maintenance exports a meeting as markdown before it goes (User guide).

Is it a vector database or a source code indexer?

No. n2n-nexus coordinates project metadata, messages, meetings, docs, tasks and assets; it does no semantic code search.

📖 Documentation

  • Installation guide: Installing, upgrading and removing the host and the client; Codex hook trust, other MCP clients, several machines.
  • User guide: Using n2n-nexus: the tray, direct messages, troubleshooting; commands, environment variables, settings.json, data and logs.
  • Architecture: System design and host-client separation explained.
  • Tools reference: Full tool list and parameters.
  • AI Assistant Guide: How AI assistants should call tools and stay in project context.
  • Host development: Building, testing and releasing the host.
  • Contributing: Development setup, and how to report issues and contribute.
  • Changelog: Version history and release notes.
  • Security: Security model, and how to report vulnerabilities.
  • Chinese README: This page in Chinese; every document above has a Chinese version.
  • llms.txt: Index of the docs for AI models.

📄 License

This project is licensed under the Apache-2.0 License.

Built by N2NS Lab, the open-source lab of datafrog.io for practical AI developer tools.

相关 MCP