준거 작업, 공유 메모리, 감사 및 MCP 클라이언트에 대한 롤백 Claude Desktop, Cursor, Claude Code. 현지에서 0 메모리 및 정책 평가 워크플로를 위한 구성 (SQLite), 또는 연결 Novyx Cloud for policy-as-code, 승인 워크플로우, 관리 대시보드, 런타임 v2, 재생 및 eval 기본. 위협 인텔리전스 및 방어 트랙링 도구는 2.9.0에서 제거되었으며 아무것도 시행하지 않았습니다. 2.9.0 이상으로 업그레이드하십시오.

먼저 시도하는 것

Novyx MCP를 사용하여 에이전트가 대신 검토 가능한 공유 메모리 필요 untracked 컨텍스트 sprawl:

그 워크플로는 영구적이기 전에 에이전트 메모리를 검토합니다. 더 보기 동일한 서버는 또한 주관 작업 도구를 노출 (action_submit, list_pending, approve_action, explain_action]) 당신이 그것을 연결할 때 Novyx 클라우드.

설치

구성

Claude 데스크탑

claude_desktop_config.json에 추가:

# # # 커서

Cursor MCP 설정에 추가:

Claude 코드

Claude Code 시작하기 전에 NOVYX_API_KEY 환경 변수를 설정합니다. 로컬 모드(SQLite, Zero config)를 사용하도록 합니다.

CLAUDE.md 통합

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: