MCP SysOperator
Allows executing Ansible playbooks and ad-hoc commands, managing inventories, validating playbook syntax, and previewing tasks for automated infrastructure operations.
Enables infrastructure management through Terraform, supporting core operations like init, plan, apply, and destroy, with additional support for LocalStack and tflocal integration.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP SysOperator run the site.yml playbook using the production inventory"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP SysOperator
A Model Context Protocol (MCP) server for Infrastructure as Code operations. This server allows AI assistants to interact with Ansible and Terraform, execute playbooks and Terraform plans, manage cloud resources, and perform other infrastructure operations directly.
(Project previously known as mcp-ansible)
Demo Projects
All code in demos generated using Claude 3.7 Sonnet (via OpenRouter), Cline, and SysOperator
AWS LAMP Stack - All Ansible code to deploy example LAMP stack in AWS
AWS Terraform LAMP - Terraform and Ansible code to reply a LAMP stack
Features
Run Ansible Playbooks: Execute Ansible playbooks with support for parameters like inventory, extra vars, tags, and limits
List Inventory: View hosts and groups from an Ansible inventory file
Check Syntax: Validate Ansible playbook syntax without execution
List Tasks: Preview tasks that would be executed by a playbook
Access Default Inventory: Access the default Ansible inventory file via resource API
AWS Integration: Manage AWS resources (EC2, S3, VPC, CloudFormation, etc.)
Terraform Support: Execute Terraform commands (init, plan, apply, destroy, output, etc.)
tflocal Integration: Test Terraform configurations with LocalStack for local cloud development
LocalStack Support: Test AWS operations locally using LocalStack without real AWS credentials
Requirements
Node.js 18 or higher
npm or yarn
Ansible installed and in PATH
@modelcontextprotocol/sdk (installed automatically)
For AWS operations: AWS CLI and valid credentials
For LocalStack: LocalStack installed and running, awslocal CLI
Installation
1. Clone the repository
git clone https://github.com/tarnover/mcp-sysoperator.git
cd mcp-sysoperator2. Install dependencies
npm install3. Build the server
npm run build4. Configure MCP settings
Add the Ansible MCP server to your MCP settings configuration file.
For VSCode with Claude extension:
Edit the file at
~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
For Claude Desktop app:
macOS: Edit
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows: Edit
%APPDATA%\Claude\claude_desktop_config.jsonLinux: Edit
~/.config/Claude/claude_desktop_config.json
Add the following to the mcpServers section:
{
"mcpServers": {
"sysoperator": {
"command": "node",
"args": ["/absolute/path/to/mcp-sysoperator/build/index.js"],
"env": {}
}
}
}Make sure to replace /absolute/path/to/mcp-sysoperator with the actual path to your installation.
Usage Examples
Once installed and configured, the MCP server provides the following tools to the AI assistant:
1. Run a Playbook
<use_mcp_tool>
<server_name>sysoperator</server_name>
<tool_name>run_playbook</tool_name>
<arguments>
{
"playbook": "/path/to/your/playbook.yml",
"inventory": "/path/to/inventory.ini",
"extraVars": {
"var1": "value1",
"var2": "value2"
},
"tags": "setup,configure",
"limit": "webservers"
}
</arguments>
</use_mcp_tool>2. List Inventory
<use_mcp_tool>
<server_name>sysoperator</server_name>
<tool_name>list_inventory</tool_name>
<arguments>
{
"inventory": "/path/to/inventory.ini"
}
</arguments>
</use_mcp_tool>3. Check Playbook Syntax
<use_mcp_tool>
<server_name>sysoperator</server_name>
<tool_name>check_syntax</tool_name>
<arguments>
{
"playbook": "/path/to/your/playbook.yml"
}
</arguments>
</use_mcp_tool>4. List Tasks in a Playbook
<use_mcp_tool>
<server_name>sysoperator</server_name>
<tool_name>list_tasks</tool_name>
<arguments>
{
"playbook": "/path/to/your/playbook.yml"
}
</arguments>
</use_mcp_tool>5. Access Default Inventory Resource
<access_mcp_resource>
<server_name>sysoperator</server_name>
<uri>sysoperator://inventory/default</uri>
</access_mcp_resource>6. AWS S3 Operations
<use_mcp_tool>
<server_name>sysoperator</server_name>
<tool_name>aws_s3</tool_name>
<arguments>
{
"action": "list_buckets",
"region": "us-east-1"
}
</arguments>
</use_mcp_tool>7. Terraform Init and Plan
<use_mcp_tool>
<server_name>sysoperator</server_name>
<tool_name>terraform</tool_name>
<arguments>
{
"action": "init",
"workingDir": "/path/to/terraform/project"
}
</arguments>
</use_mcp_tool>
<use_mcp_tool>
<server_name>sysoperator</server_name>
<tool_name>terraform</tool_name>
<arguments>
{
"action": "plan",
"workingDir": "/path/to/terraform/project",
"vars": {
"instance_type": "t2.micro",
"region": "us-west-2"
}
}
</arguments>
</use_mcp_tool>8. Terraform Apply
<use_mcp_tool>
<server_name>sysoperator</server_name>
<tool_name>terraform</tool_name>
<arguments>
{
"action": "apply",
"workingDir": "/path/to/terraform/project",
"autoApprove": true,
"vars": {
"instance_type": "t2.micro",
"region": "us-west-2"
}
}
</arguments>
</use_mcp_tool>9. Terraform with LocalStack (tflocal)
<use_mcp_tool>
<server_name>sysoperator</server_name>
<tool_name>terraform</tool_name>
<arguments>
{
"action": "apply",
"workingDir": "/path/to/terraform/project",
"useLocalstack": true,
"autoApprove": true,
"vars": {
"instance_type": "t2.micro",
"region": "us-west-2"
}
}
</arguments>
</use_mcp_tool>LocalStack Integration
This project includes integration with LocalStack for testing AWS operations locally without real AWS credentials. The LocalStack integration allows you to:
Test Ansible playbooks that use AWS services locally
Develop and test AWS operations without incurring AWS costs
Run tests without requiring real AWS credentials
Validate your infrastructure code before deploying to real AWS
Using LocalStack
See the LocalStack README for detailed instructions on using the LocalStack integration.
Quick start:
# Install LocalStack and awslocal CLI
pip install localstack awscli-local
# Start LocalStack
localstack start
# Run the sample playbook
node localstack/run_sample_playbook.mjsDevelopment
Project Structure
mcp-sysoperator/
├── src/
│ ├── index.ts # Main entry point
│ └── ansible-mcp-server/ # Will be renamed in filesystem in future updates
│ ├── index.ts # MCP SysOperator server implementation
│ ├── common/ # Common utilities and types
│ │ ├── errors.ts # Error definitions
│ │ ├── types.ts # Type and schema definitions
│ │ ├── utils.ts # Utility functions
│ │ └── version.ts # Version information
│ └── operations/ # Operation handlers
│ ├── ad_hoc.ts # Ansible ad-hoc commands
│ ├── aws.ts # AWS operations
│ ├── inventory.ts # Ansible inventory operations
│ ├── playbooks.ts # Ansible playbook operations
│ ├── terraform.ts # Terraform operations
│ └── vault.ts # Ansible vault operations
├── localstack/ # LocalStack integration
│ ├── README.md # LocalStack documentation
│ ├── sample_playbook.yml # Sample playbook for LocalStack
│ ├── inventory.ini # Sample inventory for LocalStack
│ ├── run_sample_playbook.mjs # Script to run sample playbook
│ └── utils.localstack.ts # Modified utils for LocalStack
├── package.json # Project configuration and dependencies
├── tsconfig.json # TypeScript configuration
└── README.md # DocumentationAdding New Features
To add new capabilities to the MCP server:
Modify
src/ansible-mcp-server/index.ts(future:src/sysoperator/index.ts)Add your new tool in the
setupToolHandlersmethodImplement a handler function for your tool in the appropriate operations file
Add the schema definition in
common/types.tsRebuild with
npm run build
⚠️ Disclaimer
SysOperator is currently in active development and undergoing extensive testing. It is not recommended for use in production environments at this time. The software may experience breaking changes, incomplete features, or unexpected behavior.
Use at your own risk.
License
MIT License - See LICENSE for details
Available Tools
18 toolsaws_cloudformationC
Manage AWS CloudFormation stacks
Inputs: action (required), region (required), stackName, templateBody, +4 more.
aws_dynamic_inventoryC
Create AWS dynamic inventory
Inputs: region (required), filters, hostnames, keyed_groups, +1 more.
aws_ec2C
Manage AWS EC2 instances (list, create, start, stop, terminate)
Inputs: action (required), region (required), instanceIds, filters, +9 more.
aws_elbC
Manage AWS Elastic Load Balancers
Inputs: action (required), region (required), name, lbType, +7 more.
aws_iamC
Manage AWS IAM roles and policies
Inputs: action (required), region (required), name, roleName, +5 more.
aws_lambdaC
Manage AWS Lambda functions
Inputs: action (required), region (required), name, zipFile, +12 more.
aws_rdsC
Manage AWS RDS database instances
Inputs: action (required), region (required), dbInstanceIdentifier, dbEngine, +10 more.
aws_route53C
Manage AWS Route53 DNS records and zones
Inputs: action (required), region (required), zoneId, zoneName, +6 more.
aws_s3C
Manage AWS S3 buckets and objects
Inputs: action (required), region (required), bucket, objectKey, +5 more.
aws_vpcC
Manage AWS VPC networks
Inputs: action (required), region (required), vpcId, cidrBlock, +5 more.
check_syntaxA
Check syntax of an Ansible playbook without executing it
Inputs: playbook (required).
list_inventoryC
List Ansible inventory hosts and groups
Inputs: inventory.
list_tasksC
List all tasks that would be executed by a playbook
Inputs: playbook (required).
run_ad_hocC
Run an Ansible ad-hoc command against specified hosts
Inputs: pattern (required), module, args, inventory, +2 more.
run_playbookC
Run an Ansible playbook
Inputs: playbook (required), extraVars, inventory, tags, +1 more.
terraformC
Execute Terraform commands (init, plan, apply, destroy, validate, output, etc.)
Inputs: action (required), workingDir (required), varFiles, vars, +8 more.
vault_decrypt_stringC
Decrypt a string encrypted with Ansible Vault
Inputs: string (required), vault_id, vault_password_file.
vault_encrypt_stringC
Encrypt a string using Ansible Vault
Inputs: string (required), vault_id, vault_password_file, name.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 18 tools
The tools are clearly organized into AWS service management (e.g., aws_ec2, aws_s3), Ansible operations (e.g., run_playbook, list_inventory), and Terraform/Vault utilities, with minimal overlap. However, aws_cloudformation and terraform both handle infrastructure-as-code, which could cause slight confusion in selection, though their descriptions clarify distinct purposes.
Most tools follow a consistent snake_case pattern with clear verb_noun or service_action naming (e.g., aws_ec2, run_playbook, vault_encrypt_string). The main deviation is 'terraform', which lacks a verb prefix, but this is minor given its distinct domain and common usage.
With 18 tools, the count is reasonable for the broad scope of cloud infrastructure and automation management, covering AWS, Ansible, Terraform, and Vault. It might feel slightly heavy, but each tool addresses a specific, necessary function without obvious redundancy.
The toolset provides comprehensive coverage for cloud infrastructure operations: AWS services have full lifecycle management (e.g., create, list, manage), Ansible includes playbook execution, syntax checking, and inventory handling, and Terraform/Vault cover essential commands. No significant gaps are apparent for the intended domain.
Related MCP Connectors
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Devopness MCP server for DevOps happiness! Empower AI Agents to deploy apps and infra, to any cloud.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.