novyx-mcp

<!-- mcp-name: io.github.novyxlabs/novyx-mcp -->
# novyx-mcp

Persistent memory + governance for AI agents. 119 MCP tools for **Claude Desktop**, **Cursor**, and **Claude Code**. Works locally with zero config (SQLite) for core memory operations, or connects to Novyx Cloud for the full surface including policy-as-code, approval workflows, governance dashboard, Runtime v2 agents/missions/capabilities, threat intelligence, auto-defense, correlation, governed actions, cortex, replay, and eval baselines. Every Novyx customer makes every other customer safer.

## Install

```bash
pip install novyx-mcp
```

## Configuration

### Claude Desktop

Add to your `claude_desktop_config.json`:

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

### Cursor

Add to your Claude MCP settings:

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

### Claude Code

```bash
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:

```markdown
## 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,