针对MCP客户端的管理操作、共享内存、审计和回滚，如 Claude 桌面、光标和Claude代码。本地工作，零值 用于内存和策略评估工作流的配置（SQLite），或连接到 Novyx Cloud 用于政策即代码、审批工作流程、治理仪表盘， 运行时 v2、回放和评估基线。威胁情报和 防御追踪工具在2.9.0版本中被移除，且从未强制执行; 升级到2.9.0或更高版本。

先试什么

当编码代理需要可审查共享内存时，使用 Novyx MCP 代替 未追踪上下文蔓延：

该工作流程保持代理内存可访问，防止其永久保存。该流程 同一服务器还会暴露受控操作工具（[action_submit， 当你将其连接到 时 list_pending， approve_action， explain_action） Novyx Cloud。

安装

配置

克劳德桌面

补充你的claude_desktop_config.json：

光标

添加到你的光标MCP设置中：

克劳德·科德

在开始 Claude Code 之前设置 NOVYX_API_KEY 环境变量。省略它，改用本地模式（SQLite，零配置）。

CLAUDE.md 整合

novyx-mcp

Governed actions, shared memory, audit, and rollback for MCP clients such as Claude Desktop, Cursor, and Claude Code. Works locally with zero config (SQLite) for memory and policy-evaluation workflows, or connects to Novyx Cloud for policy-as-code, approval workflows, governance dashboards, Runtime v2, replay, and eval baselines. The threat-intelligence and defense-tracking tools were removed in 2.9.0 and never enforced anything; upgrade to 2.9.0 or later.

What To Try First

Use Novyx MCP when coding agents need reviewable shared memory instead of untracked context sprawl:

draft_memory(
  observation="Deploys fail if REDIS_URL is unset in staging",
  tags=["ops", "staging"],
  importance=8,
  branch_id="staging-fixes"
)

memory_branch("staging-fixes")
draft_diff("drf_abc123")
merge_branch("staging-fixes")

That workflow keeps agent memory reviewable before it becomes permanent. The same server also exposes governed-action tools (action_submit, list_pending, approve_action, explain_action) when you connect it to Novyx Cloud.

Install

pip install novyx-mcp

Configuration

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "novyx-memory": {
      "command": "python",
      "args": ["-m", "novyx_mcp"],
      "env": {
        "NOVYX_API_KEY": "nram_your_key_here"
      }
    }
  }
}

Cursor

Add to your Cursor MCP settings:

{
  "mcpServers": {
    "novyx-memory": {
      "command": "python",
      "args": ["-m", "novyx_mcp"],
      "env": {
        "NOVYX_API_KEY": "nram_your_key_here"
      }
    }
  }
}

Claude Code

claude mcp add novyx-memory -- python -m novyx_mcp

Set the NOVYX_API_KEY environment variable before starting Claude Code. Omit it to use local mode (SQLite, zero config).

CLAUDE.md Integration

After installing and configuring the MCP server above, add this to your project’s CLAUDE.md so Claude Code uses Novyx automatically:

## Shared Memory (Novyx MCP)
You have access to novyx-mcp tools for shared memory, knowledge graph, audit,
rollback, replay, and context spaces. Use them when relevant. Store decisions
and status at the end of tasks. Check for context from other agents before
starting new work.

This turns isolated Claude Code sessions into a coordinated team — each session stores what it learned and checks what other sessions have done before starting work.

Canonical Workflow: Draft, Review, Merge

This is the highest-signal Novyx workflow for coding agents: