# Awaitless MCP server

> Provides a durable execution layer for coding agents to manage job lifecycles, concurrency queues, and results across local, SSH, and Slurm environments.

- Repository: https://github.com/xpluspro/Awaitless
- Page: https://hostedmcp.org/servers/xpluspro/awaitless
- Transport: stdio
- Stars: 1
- License: MIT
- Latest version: 0.8.0

## Install

### Claude Code

```sh
claude mcp add awaitless -- uvx awaitless-runner
```

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

```json
{
  "mcpServers": {
    "awaitless": {
      "command": "uvx",
      "args": [
        "awaitless-runner"
      ]
    }
  }
}
```

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

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

### VS Code CLI

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

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

```json
{
  "mcpServers": {
    "awaitless": {
      "command": "uvx",
      "args": [
        "awaitless-runner"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add awaitless -- uvx awaitless-runner
```

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

```toml
[mcp_servers.awaitless]
command = "uvx"
args = ["awaitless-runner"]
```

### Gemini CLI

```sh
gemini mcp add -s user awaitless uvx -- awaitless-runner
```

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

```json
{
  "mcpServers": {
    "awaitless": {
      "command": "uvx",
      "args": [
        "awaitless-runner"
      ]
    }
  }
}
```

## FAQ

### What environments can Awaitless run jobs in?

Awaitless supports running workloads across local machines, SSH hosts, and Slurm clusters.

### How does Awaitless handle long-running jobs if the client disconnects?

Jobs are durable with stable IDs, meaning state, logs, and artifacts survive client disconnects and can be recovered later.

### Can I limit how many jobs run on a specific resource?

Yes, you can create named FIFO queues with fixed concurrency to prevent too many jobs from entering a resource at once.
