The SkyeNet-MCP-ACE server enables AI agents to interact with ServiceNow instances through server-side JavaScript execution, CRUD operations, and update set management, with built-in context bloat reduction.
Core Capabilities:
Execute Server-Side JavaScript: Run server-side JavaScript directly on ServiceNow instances with configurable application scopes, timeout controls (1-300 seconds), auto-truncation of large outputs, and support for loading scripts from local files using
{{file:path}}placeholdersPerform Table Operations: Execute full CRUD operations (GET, POST, PUT, PATCH, DELETE) on any ServiceNow table with query syntax, batch operations, pagination, field filtering, display value resolution, and field validation to prevent injection attacks
Manage Update Sets: Handle complete update set lifecycle including create, set/show/clear working sets, insert/update records, rehome XMLs, view contents and recent activity, complete, reopen, delete, and diff against Default update set
Context Bloat Reduction: Use minimal, compact, and quiet response modes to reduce token usage by 90%+ through field truncation, record limiting, and removal of redundant dataβpreventing AI context overflow
Security & Validation: Sandbox execution environment, field validation to prevent injection attacks, scope-aware operations, and flexible credential management via environment variables, project
.envfiles, or system-wide filesIntegration Features: Designed for Cursor IDE and Codex compatibility with system-wide or project-level deployment options, bulletproof deployment scripts for Linux, response times under 3 seconds, and optimized memory usage
SkyeNet-MCP-ACE
ServiceNow Background Script Execution for AI Agents - A Model Context Protocol (MCP) server that enables AI agents to execute server-side JavaScript directly on ServiceNow instances with context bloat reduction features.
π Quick Start
Prerequisites
Node.js 20+ (system-wide installation recommended for Linux, nvm works on macOS)
ServiceNow instance with API access
Root/sudo access for system-wide installation (Linux only)
Installation
For Local Development (macOS/Linux)
For System-Wide Installation (Linux)
Note: The deployment scripts are Linux-specific. For macOS, use local development mode or configure manually.
Configuration
The MCP server supports multiple ways to provide credentials, checked in priority order:
Environment variables in MCP config (highest priority) - Recommended for project-specific configs
Project directory - In the SkyeNet-MCP-ACE repository root
Home directory - Global/shared credentials
System directory - Linux system-wide fallback
Option 1: Environment Variables in MCP Config (Recommended)
When configuring the MCP server in Cursor (.cursor/mcp.json), you can pass credentials directly:
Advantages: Project-specific credentials, no separate .env files needed, works from any project folder.
Option 2: Environment File
Create your ServiceNow credentials file:
Required environment variables:
Note: You can also place .servicenow-ace.env in the project root directory for project-specific credentials.
Cursor IDE Integration
For Cursor IDE (Project-Level Configuration)
Create .cursor/mcp.json in your project folder:
Replace /absolute/path/to/SkyeNet-MCP-ACE with the actual path to this repository. See .cursor/mcp.json.example for a template.
Note: If credentials are provided via the env field, they take highest priority over any .env files.
For Codex (System-Wide Configuration)
Add to your Codex configuration (/etc/codex/config.toml):
π οΈ Available Tools
1. execute_background_script
Execute server-side JavaScript directly on ServiceNow instances.
Parameters:
script(string): The JavaScript code to executequiet(boolean, optional): Ultra-minimal response mode
Example:
2. execute_table_operation
Perform CRUD operations on ServiceNow tables with context bloat reduction.
Parameters:
operation(string): GET, POST, PUT, DELETEtable(string): Table name (e.g., 'sys_user', 'incident')sys_id(string, optional): Record sys_id for specific operationssys_ids(array, optional): Multiple sys_ids for batch operationsfields(array, optional): Specific fields to retrievequery(string, optional): Encoded query stringlimit(number, optional): Maximum records to returnstrict_fields(boolean, optional): Enable strict field validationresponse_mode(string, optional): 'minimal' for reduced response size
Examples:
3. execute_updateset_operation
Manage ServiceNow Update Sets with context bloat reduction.
Parameters:
operation(string): recent, contents, set_working, get_workingupdate_set_sys_id(string, optional): Update Set sys_idresponse_mode(string, optional): 'minimal' for reduced response sizequiet(boolean, optional): Ultra-minimal response mode
Examples:
π§ Context Bloat Reduction Features
Minimal Mode
Table API: Truncates large fields, limits records, removes redundant data
Update Sets: Limits to 5 records, compact summaries, flattened structure
Background Scripts: Truncates output, removes verbose logging
Quiet Mode
Ultra-minimal responses: Only success/failure status
No verbose output: Essential information only
Reduced token usage: 90%+ reduction in response size
Response Size Examples
Standard Table API: ~15KB
Minimal Table API: ~700 bytes
Quiet Update Set: ~300 bytes
Minimal Update Set: ~2.6KB
π Maintenance
Update Installation
Clean Reinstall
π¨ Troubleshooting
Server Won't Start
Codex Timeout Issues
Permission Issues
π Project Structure
π― Key Features
Context Bloat Reduction: Minimal and quiet modes for AI agents
Bulletproof Deployment: Handles all edge cases automatically
Multi-User Compatibility: Works for all users system-wide
Comprehensive Verification: Tests all scenarios
ServiceNow Integration: Direct API access with error handling
Update Set Management: Full lifecycle support
Table Operations: CRUD with field validation
π Security
Credential Management: Separate from MCP-Connect
Field Validation: Prevents injection attacks
Error Handling: Secure error responses
System-wide Installation: Proper permissions
π Performance
Response Times: < 3 seconds for most operations
Memory Usage: Optimized for AI agent interactions
Token Efficiency: 90%+ reduction in context bloat
Reliability: Bulletproof deployment ensures stability
For detailed deployment instructions, see the bulletproof deployment script comments.