An MCP server that brings ServiceNow Fluent SDK capabilities to AI-assisted development environments. Enables natural language interaction with ServiceNow SDK commands, API specifications, code snippets, and development resources.

• 🤖 AI-Powered Error Analysis - Intelligent diagnosis with root cause, solutions, and prevention tips (MCP Sampling)
• Complete SDK Coverage - All ServiceNow SDK commands: auth, init, build, install, dependencies, transform, download, clean, pack
• Rich Resources - API specifications, code snippets, instructions for 35+ metadata types
• Multi-Environment Auth - Supports basic and oauth authentication with profile management
• Session-Aware - Maintains working directory context across commands

This MCP server implements the complete Model Context Protocol specification with the following capabilities:

• Resources - Provides 100+ resources across 35+ ServiceNow metadata types (API specs, instructions, snippets, prompts)
• Tools - Exposes 10 ServiceNow SDK commands as MCP tools with full parameter validation
• Prompts - Offers development workflow templates for common ServiceNow tasks
• Roots - Supports MCP roots protocol for workspace-aware operations

• Sampling (MCP 2024-11-05) - Leverages client LLM for intelligent error analysis when SDK commands fail

  • Automatically analyzes command errors >50 characters
  • Provides structured diagnostics: root cause, solutions, prevention tips
  • Configurable via FLUENT_MCP_ENABLE_ERROR_ANALYSIS environment variable

• Elicitation (MCP 2024-11-05) - Interactive parameter collection for complex workflows

  • init_fluent_app - Prompts for missing project parameters (workingDirectory, template, appName, etc.)
  • Supports both creation and conversion workflows with smart validation
  • Handles user acceptance/rejection of elicited data

• Session Management - Tracks working directory per session for multi-project workflows

• Root Fallback - Automatically falls back to MCP root context when no session directory is set

• Error Handling - Comprehensive error messages with actionable guidance

• Type Safety - Full TypeScript implementation with strict typing

# Test with MCP Inspector
npx @modelcontextprotocol/inspector npx @modesty/fluent-mcp

# Or use in your MCP client (see Configuration below)

Example prompt:

Create a new Fluent app in ~/projects/time-off-tracker to manage employee PTO requests

Note: manage_fluent_auth, init_fluent_app, and download_fluent_dependencies are interactive commands. Use init_fluent_app to establish working directory context for subsequent commands.

Standardized URI patterns following MCP specification:

Core Types: acl, application-menu, business-rule, client-script, cross-scope-privilege, form, list, property, role, scheduled-script, script-action, script-include, scripted-rest, service-portal, table, ui-action, ui-page, user-preference

Table Types: column, column-generic

ATF (Automated Test Framework): atf-appnav, atf-catalog-action, atf-catalog-validation, atf-catalog-variable, atf-email, atf-form, atf-form-action, atf-form-declarative-action, atf-form-field, atf-reporting, atf-rest-api, atf-rest-assert-payload, atf-server, atf-server-catalog-item, atf-server-record

Requirements: Node.js 22.15.1+, npm 11.4.1+

Add to your MCP client configuration file:

{
  "mcpServers": {
    "fluent-mcp": {
      "command": "npx",
      "args": ["-y", "@modesty/fluent-mcp"],
      "env": {
        "SN_INSTANCE_URL": "https://your-instance.service-now.com",
        "SN_AUTH_TYPE": "oauth"
      }
    }
  }
}

Client-Specific Locations:

• Claude Desktop / macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• VSCode Copilot: .vscode/mcp.json (use Command Palette: MCP: Add Server...)
• Cursor: Settings → Features → MCP Settings
• Windsurf: Settings → Cascade → MCP Servers → View raw config
• Gemini CLI: ~/.gemini/settings.json

VSCode note: For VSCode, the JSON structure uses "mcp": { "servers": { ... } } instead of "mcpServers".

Environment Variables:

• SN_INSTANCE_URL - ServiceNow instance URL (optional, can use auth profiles instead)
• SN_AUTH_TYPE - Authentication method: basic or oauth (optional)
• FLUENT_MCP_ENABLE_ERROR_ANALYSIS - Enable AI error analysis (default: true)
• FLUENT_MCP_MIN_ERROR_LENGTH - Minimum error length for analysis (default: 50)

1. Setup Authentication

   Create a new auth profile for https://dev12345.service-now.com with alias dev-instance
   

2. Initialize Project

   Create a new Fluent app in ~/projects/asset-tracker for IT asset management
   

3. Develop with Resources

   Show me the business-rule API specification and provide an example snippet
   

4. Build and Deploy

   Build the app with debug output, then deploy to dev-instance
   

The MCP Inspector provides a web interface for testing MCP servers.

# Test published package
npx @modelcontextprotocol/inspector npx @modesty/fluent-mcp

# Or for local development
npm run build && npm run inspect

Objective: Access API specs and code snippets for business rules

Steps:

1. Launch Inspector and wait for server connection
2. Navigate to Resources tab
3. Find and click sn-spec://business-rule in the resource list
4. Review the API specification showing all available methods and parameters
5. Go back and search for sn-snippet://business-rule/0001
6. Click the snippet to view a complete TypeScript example
7. Verify content includes proper imports and follows Fluent patterns

Expected Results:

• API spec displays structured documentation with method signatures
• Snippet shows runnable TypeScript code with ServiceNow metadata patterns
• Content is properly formatted and readable

Objective: Verify SDK version and help information retrieval

Steps:

1. Navigate to Tools tab
2. Select sdk_info from the tool list
3. Test Version:
   • Set flag parameter to -v
   • Click Execute
   • Verify response shows version number (e.g., "4.0.1")
4. Test Help:
   • Set flag parameter to -h
   • Set command parameter to build
   • Click Execute
   • Verify response shows build command documentation with options
5. Monitor Notifications pane for command execution logs

Expected Results:

• Version command returns SDK version string
• Help command returns detailed command documentation
• No errors in notifications pane
• Commands execute within 2-3 seconds

MIT