# slimctx MCP server

> Compresses AI agent context like logs, JSON, and code to reduce token usage while allowing byte-exact retrieval of original content.

- Repository: https://github.com/omkar9854/token_optimizer
- Page: https://hostedmcp.org/servers/omkar9854/token-optimizer
- Transport: stdio
- Stars: 1
- License: Apache-2.0
- Latest version: 0.1.0

## Install

### Claude Code

```sh
claude mcp add token-optimizer -- uvx slimctx
```

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

```json
{
  "mcpServers": {
    "token-optimizer": {
      "command": "uvx",
      "args": [
        "slimctx"
      ]
    }
  }
}
```

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

```json
{
  "servers": {
    "token-optimizer": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "slimctx"
      ]
    }
  }
}
```

### VS Code CLI

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

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

```json
{
  "mcpServers": {
    "token-optimizer": {
      "command": "uvx",
      "args": [
        "slimctx"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add token-optimizer -- uvx slimctx
```

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

```toml
[mcp_servers.token-optimizer]
command = "uvx"
args = ["slimctx"]
```

### Gemini CLI

```sh
gemini mcp add -s user token-optimizer uvx -- slimctx
```

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

```json
{
  "mcpServers": {
    "token-optimizer": {
      "command": "uvx",
      "args": [
        "slimctx"
      ]
    }
  }
}
```

## FAQ

### Is the compression reversible?

Yes, every lossy transform is byte-exact reversible, allowing the original content to be retrieved at any time.

### Does it require external dependencies or network calls?

No, it is a zero-dependency tool built with the Python standard library that requires no downloads or network calls.
