Fluent (ServiceNow SDK)
Manage ServiceNow metadata, modules, records, and tests using Fluent, a TypeScript-based declarative DSL. Supports all ServiceNow SDK CLI commands.
Fluent MCP Server
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.
Key Features
- 🤖 AI-Powered Error Analysis - Intelligent diagnosis with root cause, solutions, and prevention tips (MCP Sampling)
- Complete SDK Coverage - ServiceNow SDK commands:
init,build,install,dependencies,transform,download,clean,pack - Rich Resources - API specifications, code snippets, instructions for 48+ metadata types
- Auto-Authentication - Automatic auth profile detection and session management via environment variables
- Session-Aware - Maintains working directory and auth context across commands
This MCP server implements the complete Model Context Protocol specification with the following capabilities:
Core
- Resources - Provides 234+ resources across 48+ ServiceNow metadata types (API specs, instructions, snippets, prompts)
- Tools - Exposes 9 ServiceNow SDK commands as MCP tools with full parameter validation
- Prompts - Offers development workflow templates for common ServiceNow tasks
- Logging - Structured logging for debugging and monitoring
Client Capabilities (used by this server)
The server leverages these MCP client capabilities when available:
-
Roots - Requests workspace roots from the client for context-aware operations
- Falls back to project root when client doesn't provide roots
-
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_ANALYSISenvironment 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
Quick Start
# 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
Available Tools
SDK Commands
| Tool | Description | Key Parameters |
|---|---|---|
sdk_info | Get SDK version or help | flag (-v/-h), command (optional for -h) |
get-api-spec | Get API spec or list all metadata types | metadataType (optional, omit to list all) |
init_fluent_app | Initialize or convert ServiceNow app | workingDirectory (required), template, from (optional) |
build_fluent_app | Build the application | debug (optional) |
deploy_fluent_app | Deploy to ServiceNow instance | auth (auto-injected), debug (optional) |
fluent_transform | Convert XML to Fluent TypeScript | from, auth (auto-injected) |
download_fluent_dependencies | Download dependencies and type definitions | auth (auto-injected) |
download_fluent_app | Download metadata from instance | directory, incremental (optional) |
clean_fluent_app | Clean output directory | source (optional) |
pack_fluent_app | Create installable artifact | source (optional) |
Note: Authentication is automatically configured at startup via environment variables. The
authparameter is auto-injected from the session for commands that require instance access. Useinit_fluent_appto establish working directory context for subsequent commands.
Resources
Standardized URI patterns following MCP specification:
| Resource Type | URI Pattern | Example | Purpose |
|---|---|---|---|
| API Specs | sn-spec://{type} | sn-spec://business-rule | API documentation and parameters |
| Instructions | sn-instruct://{type} | sn-instruct://script-include | Best practices and guidance |
| Code Snippets | sn-snippet://{type}/{id} | sn-snippet://acl/0001 | Practical code examples |
| Prompts | sn-prompt://{id} | sn-prompt://coding_in_fluent | Development guides |
Supported Metadata Types
Core Types: acl, application-menu, business-rule, client-script, cross-scope-privilege, email-notification, form, import-set, list, property, role, scheduled-script, script-action, script-include, scripted-rest, service-portal, sla, table, ui-action, ui-page, ui-policy, user-preference
Table Types: column, column-generic
Service Catalog: catalog-item, catalog-item-record-producer, catalog-ui-policy, catalog-client-script, catalog-variable, variable-set
Automation & Workflow: flow
Workspace & Analytics: workspace, dashboard
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
Configuration
Requirements: Node.js 22.15.1+, npm 11.4.1+
MCP Client Setup
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": "basic",
"SN_USER_NAME": "local-username",
"SN_PASSWORD": "local-password"
}
}
}
}
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:
| Variable | Description | Default |
|---|---|---|
SN_INSTANCE_URL | ServiceNow instance URL for auto-auth validation | - |
SN_AUTH_TYPE | Authentication method: basic or oauth | oauth |
SN_USER_NAME | Username for basic auth (informational) | - |
SN_PASSWORD | Password for basic auth (informational) | - |
FLUENT_MCP_ENABLE_ERROR_ANALYSIS | Enable AI error analysis | true |
FLUENT_MCP_MIN_ERROR_LENGTH | Minimum error length for analysis | 50 |
Note: The server automatically detects existing auth profiles matching
SN_INSTANCE_URLat startup. If a matching profile is found, it's stored in the session and auto-injected into SDK commands. If no profile exists, you'll be prompted to run the auth command manually.
Usage Examples
Typical Workflow
-
Initialize Project
Create a new Fluent app in ~/projects/asset-tracker for IT asset management -
Develop with Resources
Show me the business-rule API specification and provide an example snippet -
Build and Deploy
Build the app with debug output, then deploy it
Note: Authentication is automatically configured via environment variables (
SN_INSTANCE_URL,SN_AUTH_TYPE). If you need to set up a new auth profile, run:npx @servicenow/sdk auth --add <instance-url> --type <basic|oauth> --alias <alias>
Testing with MCP Inspector
The MCP Inspector provides a web interface for testing MCP servers.
Launch Inspector
# Test published package
npx @modelcontextprotocol/inspector npx @modesty/fluent-mcp
# Or for local development
npm run build && npm run inspect
Test Scenarios
Scenario 1: Explore Business Rule Resources
Objective: Access API specs and code snippets for business rules
Steps:
- Launch Inspector and wait for server connection
- Navigate to Resources tab
- Find and click
sn-spec://business-rulein the resource list - Review the API specification showing all available methods and parameters
- Go back and search for
sn-snippet://business-rule/0001 - Click the snippet to view a complete TypeScript example
- 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
Scenario 2: Test SDK Info Command
Objective: Verify SDK version and help information retrieval
Steps:
- Navigate to Tools tab
- Select
sdk_infofrom the tool list - Test Version:
- Set
flagparameter to-v - Click Execute
- Verify response shows version number (e.g., "4.0.1")
- Set
- Test Help:
- Set
flagparameter to-h - Set
commandparameter tobuild - Click Execute
- Verify response shows build command documentation with options
- Set
- Monitor Notifications pane for command execution logs
Expected Results:
- Version command returns SDK version string
- Help command returns detailed command documentation
- List metadata (
-lm) returns available Fluent metadata types - No errors in notifications pane
- Commands execute within 2-3 seconds
License
MIT
相关服务器
Scout Monitoring MCP
赞助Put performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
赞助Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Bazaar MCP Server
MCP server providing x402 micropayment-powered developer tools including screenshot capture, AI analysis, PDF generation, code security scanning, and dependency auditing via USDC payments on Base.
302AI Basic MCP Server
A toolkit for enhancing the fundamental capabilities of large language models.
Credos
Share your team's Coding Best Practices with Cursor, VS Code, Claude code, Windsurf, JetBrains IDEs and other coding tools supporting remote MCP connection.
Jetty.io
Work on dataset metadata with MLCommons Croissant validation and creation.
Volatility MCP
Integrates Volatility 3 memory analysis with FastAPI and MCP, exposing memory forensics plugins via REST APIs.
Lean LSP
Interact with the Lean theorem prover via the Language Server Protocol (LSP), enabling LLM agents to understand, analyze, and modify Lean projects.
IIIF Images Server
A server for working with IIIF (International Image Interoperability Framework) manifests and images.
EChart Server
A Go service that dynamically generates ECharts chart pages from JSON configurations.
DevStandards
Provides AI agents with access to development best practices, security guidelines, and coding standards.
Docker MCP
A Ruby implementation of an MCP server for managing and using Docker