# Defenter Proxy MCP server

> Provides real-time semantic security for AI coding agents by monitoring prompts, MCP tool calls, and file operations to prevent data leaks.

- Repository: https://github.com/Defenter-AI/defenter-proxy
- Page: https://hostedmcp.org/servers/defenter-ai/defenter-proxy
- Transport: stdio
- Stars: 3
- License: Apache-2.0
- Latest version: 0.0.96

## Install

### Claude Code

```sh
claude mcp add defenter-proxy -- uvx defenter-proxy
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "defenter-proxy": {
      "command": "uvx",
      "args": [
        "defenter-proxy"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "defenter-proxy": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "defenter-proxy"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"defenter-proxy","type":"stdio","command":"uvx","args":["defenter-proxy"]}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "defenter-proxy": {
      "command": "uvx",
      "args": [
        "defenter-proxy"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add defenter-proxy -- uvx defenter-proxy
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.defenter-proxy]
command = "uvx"
args = ["defenter-proxy"]
```

### Gemini CLI

```sh
gemini mcp add -s user defenter-proxy uvx -- defenter-proxy
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "defenter-proxy": {
      "command": "uvx",
      "args": [
        "defenter-proxy"
      ]
    }
  }
}
```

## FAQ

### What does Defenter monitor?

It monitors every prompt, coding agent tool call, MCP server call, and key file and shell operations within your IDE.

### How do I use Defenter with MCP?

Once the extension is installed, it automatically intercepts MCP server calls without requiring manual MCP configuration.

### Which IDEs are supported?

Defenter is compatible with VS Code, Cursor, and Claude Code.

### How does the security enforcement work?

The system analyzes payloads in real time and enforces security policies using allow, redact, or block decisions.
