Dev Assistant MCP - now in Open Beta!
We're launching the Gusto Embedded Dev Assistant MCP server into Open Beta. AI-powered development tools can now connect directly to Gusto's API reference and documentation, giving your AI assistant accurate, up-to-date context instead of relying on stale LLM training data or brittle web search.
What is the Dev Assistant MCP?
The Dev Assistant MCP server implements the Model Context Protocol (MCP), an open standard for connecting AI applications to external data sources. By pointing your AI tool at Gusto's MCP server, it gains access to:
- API reference search: Fetch endpoint definitions, request/response schemas, and field-level details
- Documentation search: Retrieve guides and best practices directly from our docs
- Code generation: Produce accurate, API-aware code snippets in your language of choice
Setup
Connect to the hosted MCP server at: https://embedded-payroll.readme.io/mcp
Configuration varies by tool. For Cursor, add the following to ~/.cursor/mcp.json:
{
"mcpServers": {
"embedded-payroll": {
"url": "https://embedded-payroll.readme.io/mcp"
}
}
}See the Dev Assistant MCP setup guide for instructions for Cursor, Windsurf, Claude Desktop, and VS Code.
Example Prompts
Once connected, try asking your AI assistant:
- "How do I authenticate with the Gusto Embedded API? What are the best practices?"
- "Show me the request body schema for creating a new employee"
- "Generate a Python code snippet for running payroll"
- "What webhooks are available for payroll events?"
- "Show me an example of payroll reversals and how they work"
- "Create a mock terminations UI using the Gusto Embedded API"
- "What is the cutoff time for payroll cancellations?"
The MCP server works wherever MCP is supported—in coding tools like Cursor, VS Code, and Claude Code, or general-purpose tools like Claude Desktop for questions and UI prototyping.
Feedback & Questions
Reach out to your Technical Solutions representative with any questions or feedback about the Dev Assistant MCP, as we will continue to refine it before fully launching.