# @secr/mcp

[Secr](https://secr.dev) MCP server — gives AI coding agents (Claude Code, Cursor, Copilot) direct access to secrets via the [Model Context Protocol](https://modelcontextprotocol.io).

## Install

```bash
npm install @secr/mcp
```

## Setup

### Claude Code

```bash
claude mcp add secr -e SECR_TOKEN=secr_agent_xxx -- npx @secr/mcp
```

### Cursor

Add to `~/.cursor/mcp.json`:

```json
{
  "mcpServers": {
    "secr": {
      "command": "npx",
      "args": ["@secr/mcp"],
      "env": { "SECR_TOKEN": "secr_agent_xxx" }
    }
  }
}
```

### VS Code (Copilot)

Add to `.vscode/mcp.json`:

```json
{
  "servers": {
    "secr": {
      "command": "npx",
      "args": ["@secr/mcp"],
      "env": { "SECR_TOKEN": "secr_agent_xxx" }
    }
  }
}
```

## Tools

The server exposes 5 tools to AI agents:

| Tool | Description |
|------|-------------|
| `get_secret` | Get a single secret value by key |
| `list_secrets` | List secret key names (no values) with optional search |
| `set_secret` | Create or update a secret |
| `delete_secret` | Delete a secret |
| `list_environments` | List environments for a project |

All tools accept optional `org`, `project`, and `environment` parameters. When omitted, they resolve from environment variables or `.secr.json`.

## Environment Variables

| Variable | Required | Default | Description |
|----------|----------|---------|-------------|
| `SECR_TOKEN` | Yes | -- | Agent token (`secr_agent_...`) |
| `SECR_ORG` | No | `.secr.json` | Organization slug |
| `SECR_PROJECT` | No | `.secr.json` | Project slug |
| `SECR_ENVIRONMENT` | No | `.secr.json` | Default environment slug |
| `SECR_API_URL` | No | `https://api.secr.dev` | API base URL |

## Creating an Agent Token

```bash
secr agents create --name "claude-code" --scope "read:secrets,write:secrets"
```

Agent tokens use scoped permissions — the server only has access to what the token allows.

## Documentation

Full docs at [secr.dev/docs](https://secr.dev/docs).

## License

MIT