Cerebras MCP Code Generation

FAST code generation via mcp__cerebras-mcp__write tool using Z.ai glm-4.6 model.

When to Use

Use for rapid test and code generation when speed matters more than nuance:

✅ Test files - unit tests, integration tests, test fixtures
✅ Boilerplate - CRUD endpoints, data models, components
✅ Bulk creation - multiple similar files quickly
✅ Migrations - database migrations, schema updates
❌ NOT for complex architecture, security code, nuanced logic

Rule: Prompt must be SHORTER than expected output (blueprint style).

Usage

mcp__cerebras-mcp__write:
  file_path: /absolute/path/to/file.ts
  prompt: |
    Function: validateEmail(email: string): boolean
    Steps:
    - Regex test /^[^@]+@[^@]+\.[^@]+$/
    - Return boolean result
    Imports: none
    Errors: none
  context_files:
    - /path/to/related/file.ts

Prompt Format (Blueprint Style)

File: /path/to/file.ts
Function: functionName(params): returnType
Steps:
- Step 1
- Step 2
Imports: import { X } from './y'
Errors: throw new Error("message")

Rules

Prompt < Output: Blueprint must be shorter than generated code
Always include context_files: When code needs imports from existing files
Absolute paths only: Use full paths, not relative
One file per call: Generate/modify single file

Bad vs Good

Bad (verbose):

I need you to create a function that validates email addresses.
The function should take an email string as input and return true
if valid or false if invalid...

Good (blueprint):

Function: validateEmail(email: string): boolean
- Regex: /^[^@]+@[^@]+\.[^@]+$/
- Return: true if match, false otherwise

## Known Issues

- ℹ️ **Documentation Only**: This skill describes the MCP tool that's available in the main chat interface
- ℹ️ **No Separate Implementation**: There is no separate script to invoke - the tool is used directly
- ℹ️ **Main Chat Only**: This MCP tool is only available in the main chat, not within spawned agents