# MCP Background Job Server
[](https://www.python.org/downloads/)
[](https://github.com/jlowin/fastmcp)
[](https://badge.fury.io/py/mcp-background-job)
[](LICENSE)
An MCP (Model Context Protocol) server that enables coding agents to execute long-running shell commands asynchronously with full process management capabilities.
## Overview
The MCP Background Job Server provides a robust solution for running shell commands in the background, allowing agents to start processes, monitor their status, interact with them, and manage their lifecycle. This is particularly useful for development workflows involving build processes, test suites, servers, or any long-running operations.
## Features
- **Asynchronous Process Execution**: Execute shell commands as background jobs with unique job IDs
- **Process Lifecycle Management**: Start, monitor, interact with, and terminate background processes
- **Real-time Output Monitoring**: Capture and retrieve stdout/stderr with buffering and tailing capabilities
- **Interactive Process Support**: Send input to running processes via stdin
- **Resource Management**: Configurable job limits and automatic cleanup of completed processes
- **MCP Protocol Integration**: Full integration with Model Context Protocol for agent interactions
## Installation
### Quick Install (Recommended)
Install directly from PyPI using `uvx`:
```bash
# Install and run the MCP server
uvx mcp-background-job
```
### Claude Code Integration
Add the server to your Claude Code configuration:
1. **Option A: Using Claude Code Desktop**
- Open Claude Code settings/preferences
- Navigate to MCP Servers section
- Add a new server:
- **Name**: `background-job`
- **Command**: `uvx`
- **Args**: `["mcp-background-job"]`
2. **Option B: Configuration File**
Add to your Claude Code configuration file:
```json
{
"mcpServers": {
"background-job": {
"command": "uvx",
"args": ["mcp-background-job"]
}
}
}
```
3. **Restart Claude Code** to load the new MCP server.
### Development Setup
For local development or contributing:
#### Prerequisites
- Python 3.12 or higher
- [uv](https://docs.astral.sh/uv/) package manager
#### Setup Steps
1. **Clone and navigate to the project directory:**
```bash
git clone https://github.com/dylan-gluck/mcp-background-job.git
cd mcp-background-job
```
2. **Install dependencies:**
```bash
uv sync
```
3. **Install in development mode:**
```bash
uv add -e .
```
## Quick Start
### Using with Claude Code
Once configured, ask Claude to help you with background tasks:
```
You: "Start my development server in the background and monitor it"
Claude: I'll start your development server using the background job server.
[Uses the execute tool to run your dev server]
[Shows job ID and monitors startup progress]
[Provides status updates]
Claude: "Your development server is now running on http://localhost:3000.
The job ID is abc123-def456 if you need to control it later."
```
### Manual Server Usage
For development or direct usage:
```bash
# Run with stdio transport (most common)
uvx mcp-background-job
# Or for development:
uv run python -m mcp_background_job
```
### Basic Usage Example
```python
# 1. Execute a long-running command
execute_result = await execute_command("npm run dev")
job_id = execute_result.job_id
# 2. Check job status
status = await get_job_status(job_id)
print(f"Job status: {status.status}")
# 3. Get recent output
output = await tail_job_output(job_id, lines=20)
print("Recent output:", output.stdout)
# 4. Interact with the process
interaction = await interact_with_job(job_id, "some input\n")
print("Process response:", interaction.stdout)
# 5. Kill the job when done
result = await kill_job(job_id)
print(f"Kill result: {result.status}")
```
## MCP Tools Reference
The server exposes 7 MCP tools for process management:
### Read-only Tools
| Tool | Description | Parameters | Returns |
|------|-------------|------------|---------|
| `list` | List all background jobs | None | `{jobs: [JobSummary]}` |
| `status` | Get job status | `job_id: str` | `{status: JobStatus}` |
| `output` | Get complete job output | `job_id: str` | `{stdout: str, stderr: str}` |
| `tail` | Get recent output lines | `job_id: str, lines: int` | `{stdout: str, stderr: str}` |
### Interactive Tools
| Tool | Description | Parameters | Returns |
|------|-------------|------------|---------|
| `execute` | Start new background job | `command: str` | `{job_id: str}` |
| `interact` | Send input to job stdin | `job_id: str, input: str` | `{stdout: str, stderr: str}` |
| `kill` | Terminate running job | `job_id: str` | `{status: str}` |
### Job Status Values
- `running` - Process is currently executing
- `completed` - Process finished successfully
- `failed` - Process terminated with error
- `killed` - Process was terminated by user
## Configuration
### Environment Variables
Configure the server behavior using these environment variables:
```bash
# Maximum concurrent jobs (default: 10)
export MCP_BG_MAX_JOBS=20
# Maximum output buffer per job (default: 10MB)
export MCP_BG_MAX_OUTPUT_SIZE=20MB
# or in bytes:
export MCP_BG_MAX_OUTPUT_SIZE=20971520
# Default job timeout in seconds (default: no timeout)
export MCP_BG_JOB_TIMEOUT=3600
# Cleanup interval for completed jobs in seconds (default: 300)
export MCP_BG_CLEANUP_INTERVAL=600
# Working directory for jobs (default: current directory)
export MCP_BG_WORKING_DIR=/path/to/project
# Allowed command patterns (optional security restriction)
export MCP_BG_ALLOWED_COMMANDS="^npm ,^python ,^echo ,^ls"
```
### Claude Code Configuration with Environment Variables
```json
{
"mcpServers": {
"background-job": {
"command": "uvx",
"args": ["mcp-background-job"],
"env": {
"MCP_BG_MAX_JOBS": "20",
"MCP_BG_MAX_OUTPUT_SIZE": "20MB"
}
}
}
}
```
### Programmatic Configuration
```python
from mcp_background_job.config import BackgroundJobConfig
config = BackgroundJobConfig(
max_concurrent_jobs=20,
max_output_size_bytes=20 * 1024 * 1024, # 20MB
default_job_timeout=7200, # 2 hours
cleanup_interval_seconds=600 # 10 minutes
)
```
## Architecture
The server is built with a modular architecture:
- **JobManager**: Central service for job lifecycle management
- **ProcessWrapper**: Abstraction layer for subprocess handling with I/O buffering
- **FastMCP Server**: MCP protocol implementation with tool definitions
- **Pydantic Models**: Type-safe data validation and serialization
### Key Components
```
src/mcp_background_job/
├── server.py # FastMCP server and tool definitions
├── service.py # JobManager service implementation
├── process.py # ProcessWrapper for subprocess management
├── models.py # Pydantic data models
├── config.py # Configuration management
└── logging_config.py # Logging setup
```
## Development
### Running Tests
```bash
# Run all tests
uv run pytest tests/
# Run unit tests only
uv run pytest tests/unit/ -v
# Run integration tests only
uv run pytest tests/integration/ -v
```
### Code Formatting
```bash
# Format code with ruff
uv run ruff format
# Run type checking
uv run mypy src/
```
### Development Workflow
1. Make your changes
2. Run tests: `uv run pytest tests/`
3. Format code: `uv run ruff format`
4. Commit changes
## Examples
### Development Server Workflow
```bash
# Start a development server
job_id=$(echo '{"command": "npm run dev"}' | mcp-tool execute)
# Monitor the startup
mcp-tool tail --job_id "$job_id" --lines 10
# Check if server is ready
mcp-tool status --job_id "$job_id"
# Stop the server
mcp-tool kill --job_id "$job_id"
```
### Long-running Build Process
```bash
# Start a build process
job_id=$(echo '{"command": "docker build -t myapp ."}' | mcp-tool execute)
# Monitor build progress
while true; do
status=$(mcp-tool status --job_id "$job_id")
if [[ "$status" != "running" ]]; then break; fi
mcp-tool tail --job_id "$job_id" --lines 5
sleep 10
done
# Get final build output
mcp-tool output --job_id "$job_id"
```
### Interactive Process Example
```bash
# Start Python REPL
job_id=$(echo '{"command": "python -i"}' | mcp-tool execute)
# Send Python code
mcp-tool interact --job_id "$job_id" --input "print('Hello, World!')\n"
# Send more commands
mcp-tool interact --job_id "$job_id" --input "import sys; print(sys.version)\n"
# Exit REPL
mcp-tool interact --job_id "$job_id" --input "exit()\n"
```
## Security Considerations
- **Process Isolation**: Each job runs as a separate subprocess
- **Resource Limits**: Configurable limits on concurrent jobs and memory usage
- **Input Validation**: All parameters are validated using Pydantic models
- **Command Restrictions**: Consider implementing command allowlists in production
- **Output Sanitization**: Be aware that process output may contain sensitive information
## Transport Support
The server supports multiple MCP transports:
- **stdio**: Default transport for local development and agent integration
- **HTTP**: For remote access (requires additional setup)
For stdio transport, ensure logging goes to stderr only to avoid protocol conflicts.
## Troubleshooting
### Common Issues
**Import Errors**: Ensure the package is installed in development mode:
```bash
uv add -e .
```
**Tests Not Running**: Install the package first, then run tests:
```bash
uv sync
uv add -e .
uv run pytest tests/
```
**Permission Errors**: Ensure proper permissions for the commands you're trying to execute.
**Memory Issues**: Adjust `MCP_BG_MAX_OUTPUT_SIZE` if dealing with processes that generate large amounts of output.
## Contributing
1. Fork the repository
2. Create a feature branch
3. Make your changes with tests
4. Run the test suite and formatting
5. Submit a pull request
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
## Changelog
### v0.1.1
- Published to PyPI for easy installation via `uvx`
- Added console script entry point (`mcp-background-job`)
- Updated documentation with installation and usage instructions
- Fixed linting issues and improved code quality
### v0.1.0
- Initial implementation with full MCP tool support
- Process lifecycle management
- Configurable resource limits
- Comprehensive test suite
---
Built with ❤️ using [FastMCP](https://github.com/jlowin/fastmcp) and Python 3.12+
Raw data
{
"_id": null,
"home_page": null,
"name": "mcp-background-job",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.12",
"maintainer_email": null,
"keywords": "async, background, commands, jobs, mcp, shell",
"author": null,
"author_email": "Dylan Navajas Gluck <dylan.n.gluck@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/19/c8/3a4efe9db89b815762e25c4e30c55bef31a1de925710cbe3a46d66c15119/mcp_background_job-0.1.2.tar.gz",
"platform": null,
"description": "# MCP Background Job Server\n\n[](https://www.python.org/downloads/)\n[](https://github.com/jlowin/fastmcp)\n[](https://badge.fury.io/py/mcp-background-job)\n[](LICENSE)\n\nAn MCP (Model Context Protocol) server that enables coding agents to execute long-running shell commands asynchronously with full process management capabilities.\n\n## Overview\n\nThe MCP Background Job Server provides a robust solution for running shell commands in the background, allowing agents to start processes, monitor their status, interact with them, and manage their lifecycle. This is particularly useful for development workflows involving build processes, test suites, servers, or any long-running operations.\n\n## Features\n\n- **Asynchronous Process Execution**: Execute shell commands as background jobs with unique job IDs\n- **Process Lifecycle Management**: Start, monitor, interact with, and terminate background processes \n- **Real-time Output Monitoring**: Capture and retrieve stdout/stderr with buffering and tailing capabilities\n- **Interactive Process Support**: Send input to running processes via stdin\n- **Resource Management**: Configurable job limits and automatic cleanup of completed processes\n- **MCP Protocol Integration**: Full integration with Model Context Protocol for agent interactions\n\n## Installation\n\n### Quick Install (Recommended)\n\nInstall directly from PyPI using `uvx`:\n\n```bash\n# Install and run the MCP server\nuvx mcp-background-job\n```\n\n### Claude Code Integration\n\nAdd the server to your Claude Code configuration:\n\n1. **Option A: Using Claude Code Desktop**\n - Open Claude Code settings/preferences\n - Navigate to MCP Servers section \n - Add a new server:\n - **Name**: `background-job`\n - **Command**: `uvx`\n - **Args**: `[\"mcp-background-job\"]`\n\n2. **Option B: Configuration File**\n Add to your Claude Code configuration file:\n ```json\n {\n \"mcpServers\": {\n \"background-job\": {\n \"command\": \"uvx\",\n \"args\": [\"mcp-background-job\"]\n }\n }\n }\n ```\n\n3. **Restart Claude Code** to load the new MCP server.\n\n### Development Setup\n\nFor local development or contributing:\n\n#### Prerequisites\n\n- Python 3.12 or higher\n- [uv](https://docs.astral.sh/uv/) package manager\n\n#### Setup Steps\n\n1. **Clone and navigate to the project directory:**\n ```bash\n git clone https://github.com/dylan-gluck/mcp-background-job.git\n cd mcp-background-job\n ```\n\n2. **Install dependencies:**\n ```bash\n uv sync\n ```\n\n3. **Install in development mode:**\n ```bash\n uv add -e .\n ```\n\n## Quick Start\n\n### Using with Claude Code\n\nOnce configured, ask Claude to help you with background tasks:\n\n```\nYou: \"Start my development server in the background and monitor it\"\n\nClaude: I'll start your development server using the background job server.\n\n[Uses the execute tool to run your dev server]\n[Shows job ID and monitors startup progress]\n[Provides status updates]\n\nClaude: \"Your development server is now running on http://localhost:3000. \nThe job ID is abc123-def456 if you need to control it later.\"\n```\n\n### Manual Server Usage\n\nFor development or direct usage:\n\n```bash\n# Run with stdio transport (most common)\nuvx mcp-background-job\n\n# Or for development:\nuv run python -m mcp_background_job\n```\n\n### Basic Usage Example\n\n```python\n# 1. Execute a long-running command\nexecute_result = await execute_command(\"npm run dev\")\njob_id = execute_result.job_id\n\n# 2. Check job status\nstatus = await get_job_status(job_id)\nprint(f\"Job status: {status.status}\")\n\n# 3. Get recent output\noutput = await tail_job_output(job_id, lines=20)\nprint(\"Recent output:\", output.stdout)\n\n# 4. Interact with the process\ninteraction = await interact_with_job(job_id, \"some input\\n\")\nprint(\"Process response:\", interaction.stdout)\n\n# 5. Kill the job when done\nresult = await kill_job(job_id)\nprint(f\"Kill result: {result.status}\")\n```\n\n## MCP Tools Reference\n\nThe server exposes 7 MCP tools for process management:\n\n### Read-only Tools\n\n| Tool | Description | Parameters | Returns |\n|------|-------------|------------|---------|\n| `list` | List all background jobs | None | `{jobs: [JobSummary]}` |\n| `status` | Get job status | `job_id: str` | `{status: JobStatus}` |\n| `output` | Get complete job output | `job_id: str` | `{stdout: str, stderr: str}` |\n| `tail` | Get recent output lines | `job_id: str, lines: int` | `{stdout: str, stderr: str}` |\n\n### Interactive Tools\n\n| Tool | Description | Parameters | Returns |\n|------|-------------|------------|---------|\n| `execute` | Start new background job | `command: str` | `{job_id: str}` |\n| `interact` | Send input to job stdin | `job_id: str, input: str` | `{stdout: str, stderr: str}` |\n| `kill` | Terminate running job | `job_id: str` | `{status: str}` |\n\n### Job Status Values\n\n- `running` - Process is currently executing\n- `completed` - Process finished successfully\n- `failed` - Process terminated with error\n- `killed` - Process was terminated by user\n\n## Configuration\n\n### Environment Variables\n\nConfigure the server behavior using these environment variables:\n\n```bash\n# Maximum concurrent jobs (default: 10)\nexport MCP_BG_MAX_JOBS=20\n\n# Maximum output buffer per job (default: 10MB)\nexport MCP_BG_MAX_OUTPUT_SIZE=20MB\n# or in bytes:\nexport MCP_BG_MAX_OUTPUT_SIZE=20971520\n\n# Default job timeout in seconds (default: no timeout)\nexport MCP_BG_JOB_TIMEOUT=3600\n\n# Cleanup interval for completed jobs in seconds (default: 300)\nexport MCP_BG_CLEANUP_INTERVAL=600\n\n# Working directory for jobs (default: current directory)\nexport MCP_BG_WORKING_DIR=/path/to/project\n\n# Allowed command patterns (optional security restriction)\nexport MCP_BG_ALLOWED_COMMANDS=\"^npm ,^python ,^echo ,^ls\"\n```\n\n### Claude Code Configuration with Environment Variables\n\n```json\n{\n \"mcpServers\": {\n \"background-job\": {\n \"command\": \"uvx\",\n \"args\": [\"mcp-background-job\"],\n \"env\": {\n \"MCP_BG_MAX_JOBS\": \"20\",\n \"MCP_BG_MAX_OUTPUT_SIZE\": \"20MB\"\n }\n }\n }\n}\n```\n\n### Programmatic Configuration\n\n```python\nfrom mcp_background_job.config import BackgroundJobConfig\n\nconfig = BackgroundJobConfig(\n max_concurrent_jobs=20,\n max_output_size_bytes=20 * 1024 * 1024, # 20MB\n default_job_timeout=7200, # 2 hours\n cleanup_interval_seconds=600 # 10 minutes\n)\n```\n\n## Architecture\n\nThe server is built with a modular architecture:\n\n- **JobManager**: Central service for job lifecycle management\n- **ProcessWrapper**: Abstraction layer for subprocess handling with I/O buffering\n- **FastMCP Server**: MCP protocol implementation with tool definitions\n- **Pydantic Models**: Type-safe data validation and serialization\n\n### Key Components\n\n```\nsrc/mcp_background_job/\n\u251c\u2500\u2500 server.py # FastMCP server and tool definitions\n\u251c\u2500\u2500 service.py # JobManager service implementation \n\u251c\u2500\u2500 process.py # ProcessWrapper for subprocess management\n\u251c\u2500\u2500 models.py # Pydantic data models\n\u251c\u2500\u2500 config.py # Configuration management\n\u2514\u2500\u2500 logging_config.py # Logging setup\n```\n\n## Development\n\n### Running Tests\n\n```bash\n# Run all tests\nuv run pytest tests/\n\n# Run unit tests only\nuv run pytest tests/unit/ -v\n\n# Run integration tests only \nuv run pytest tests/integration/ -v\n```\n\n### Code Formatting\n\n```bash\n# Format code with ruff\nuv run ruff format\n\n# Run type checking\nuv run mypy src/\n```\n\n### Development Workflow\n\n1. Make your changes\n2. Run tests: `uv run pytest tests/`\n3. Format code: `uv run ruff format`\n4. Commit changes\n\n## Examples\n\n### Development Server Workflow\n\n```bash\n# Start a development server\njob_id=$(echo '{\"command\": \"npm run dev\"}' | mcp-tool execute)\n\n# Monitor the startup\nmcp-tool tail --job_id \"$job_id\" --lines 10\n\n# Check if server is ready\nmcp-tool status --job_id \"$job_id\"\n\n# Stop the server\nmcp-tool kill --job_id \"$job_id\"\n```\n\n### Long-running Build Process\n\n```bash\n# Start a build process\njob_id=$(echo '{\"command\": \"docker build -t myapp .\"}' | mcp-tool execute)\n\n# Monitor build progress\nwhile true; do\n status=$(mcp-tool status --job_id \"$job_id\")\n if [[ \"$status\" != \"running\" ]]; then break; fi\n mcp-tool tail --job_id \"$job_id\" --lines 5\n sleep 10\ndone\n\n# Get final build output\nmcp-tool output --job_id \"$job_id\"\n```\n\n### Interactive Process Example\n\n```bash\n# Start Python REPL\njob_id=$(echo '{\"command\": \"python -i\"}' | mcp-tool execute)\n\n# Send Python code\nmcp-tool interact --job_id \"$job_id\" --input \"print('Hello, World!')\\n\"\n\n# Send more commands\nmcp-tool interact --job_id \"$job_id\" --input \"import sys; print(sys.version)\\n\"\n\n# Exit REPL\nmcp-tool interact --job_id \"$job_id\" --input \"exit()\\n\"\n```\n\n## Security Considerations\n\n- **Process Isolation**: Each job runs as a separate subprocess\n- **Resource Limits**: Configurable limits on concurrent jobs and memory usage \n- **Input Validation**: All parameters are validated using Pydantic models\n- **Command Restrictions**: Consider implementing command allowlists in production\n- **Output Sanitization**: Be aware that process output may contain sensitive information\n\n## Transport Support\n\nThe server supports multiple MCP transports:\n\n- **stdio**: Default transport for local development and agent integration\n- **HTTP**: For remote access (requires additional setup)\n\nFor stdio transport, ensure logging goes to stderr only to avoid protocol conflicts.\n\n## Troubleshooting\n\n### Common Issues\n\n**Import Errors**: Ensure the package is installed in development mode:\n```bash\nuv add -e .\n```\n\n**Tests Not Running**: Install the package first, then run tests:\n```bash\nuv sync\nuv add -e .\nuv run pytest tests/\n```\n\n**Permission Errors**: Ensure proper permissions for the commands you're trying to execute.\n\n**Memory Issues**: Adjust `MCP_BG_MAX_OUTPUT_SIZE` if dealing with processes that generate large amounts of output.\n\n## Contributing\n\n1. Fork the repository\n2. Create a feature branch\n3. Make your changes with tests\n4. Run the test suite and formatting\n5. Submit a pull request\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## Changelog\n\n### v0.1.1\n- Published to PyPI for easy installation via `uvx`\n- Added console script entry point (`mcp-background-job`)\n- Updated documentation with installation and usage instructions\n- Fixed linting issues and improved code quality\n\n### v0.1.0\n- Initial implementation with full MCP tool support\n- Process lifecycle management\n- Configurable resource limits\n- Comprehensive test suite\n\n---\n\nBuilt with \u2764\ufe0f using [FastMCP](https://github.com/jlowin/fastmcp) and Python 3.12+",
"bugtrack_url": null,
"license": "MIT",
"summary": "MCP server for executing long-running shell commands asynchronously",
"version": "0.1.2",
"project_urls": {
"Homepage": "https://github.com/dylan-gluck/mcp-background-job",
"Issues": "https://github.com/dylan-gluck/mcp-background-job/issues",
"Repository": "https://github.com/dylan-gluck/mcp-background-job"
},
"split_keywords": [
"async",
" background",
" commands",
" jobs",
" mcp",
" shell"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "fd646c1b5d6b8368a138178bf759dcd54c1a5b324030b3273abc78fb2aee4bc9",
"md5": "03804e3a5449e1fc4a99b31f03cf34b8",
"sha256": "f2ef2792e2b009142d413259b8b2dbda7240092887a3084e240563eb2226b86f"
},
"downloads": -1,
"filename": "mcp_background_job-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "03804e3a5449e1fc4a99b31f03cf34b8",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.12",
"size": 18220,
"upload_time": "2025-08-06T02:01:53",
"upload_time_iso_8601": "2025-08-06T02:01:53.457326Z",
"url": "https://files.pythonhosted.org/packages/fd/64/6c1b5d6b8368a138178bf759dcd54c1a5b324030b3273abc78fb2aee4bc9/mcp_background_job-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "19c83a4efe9db89b815762e25c4e30c55bef31a1de925710cbe3a46d66c15119",
"md5": "41d493ebc4ca777d39a6001234de8a95",
"sha256": "a514ce72ae1c7383d127911e49dd6ca81d93a880be803c50f7a71e202246a079"
},
"downloads": -1,
"filename": "mcp_background_job-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "41d493ebc4ca777d39a6001234de8a95",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.12",
"size": 77891,
"upload_time": "2025-08-06T02:01:54",
"upload_time_iso_8601": "2025-08-06T02:01:54.968661Z",
"url": "https://files.pythonhosted.org/packages/19/c8/3a4efe9db89b815762e25c4e30c55bef31a1de925710cbe3a46d66c15119/mcp_background_job-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-06 02:01:54",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "dylan-gluck",
"github_project": "mcp-background-job",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "mcp-background-job"
}
JSON
