Faker System
Station’s Faker system generates realistic mock data using AI, enabling safe development and testing without production credentials.Why Fakers?
| Without Fakers | With Fakers |
|---|---|
| Need production credentials | No credentials required |
| Risk of affecting real systems | Completely isolated |
| Limited test scenarios | Unlimited realistic scenarios |
| Expensive API calls | Free, local generation |
Quick Start
Via MCP Tool
faker_create_standalone tool to set up the faker.
Via CLI
How It Works
- Receive tool calls from agents
- Use AI to generate contextually appropriate responses
- Return realistic mock data
Creating Fakers
MCP Tool (Recommended)
Programmatic
In template.json
Configuration
Goal/Instruction
Thegoal or ai-instruction guides the AI in generating appropriate data:
Good:
Tool Definitions
Define tools that match your real MCP server’s interface:Examples
Infrastructure Monitoring
Security Scanning
Cost Analysis
Incident Response
Using Fakers in Agents
Assign to Agent
In template.json
Faker vs Real MCP Server
Development with Faker
Production with Real Server
template.json files per environment to swap between faker and real.
Advanced Configuration
Persistence
By default, fakers don’t persist data between calls. For stateful scenarios:Auto-sync
Faker configurations can auto-sync to your environment:Debug Mode
Enable verbose logging to see AI prompts and responses:Testing Agents with Fakers
Generate Test Scenarios
Run Evaluation
Best Practices
- Match real schemas - Faker tool schemas should match your real MCP servers
- Be specific in goals - Detailed instructions produce more realistic data
- Include edge cases - Mention error conditions and anomalies in goals
- Version your fakers - Keep faker configs in Git alongside agents
- Test transitions - Ensure agents work with both faker and real data
Troubleshooting
Generic/Unrealistic Data
Problem: Faker returns too generic data Solution: Make the goal more specific:Schema Mismatch
Problem: Agent expects different data format Solution: Define explicit output schema in tool definition:Slow Responses
Problem: Faker takes too long Solution:- Use a faster model for fakers
- Simplify the goal
- Cache common responses
Next Steps
- Sandbox - Isolated code execution
- Evaluation - Test agent performance
- Bundles - Package agents with fakers

