fail_level
Minimum severity ("CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG")
How to use it
fail_level is exposed by the Django Ai Boost MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the fail_level tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Django Ai Boost
uv pip install django-ai-boostOther tools in Django Ai Boost (17)
The Django app label (e.g., "blog")
Optional list of app labels to filter (e.g., ["blog", "auth"]). If not provided, returns all models.
Optional list of positional arguments
Optional list of database aliases to include
Include deployment checks when true
Optional dict of field lookups (e.g., {"status": "published", "featured": true})
Optional handler name to read from a single file handler
Optional dict of keyword arguments
Maximum number of results to return (default: 100, max: 1000)
Number of lines to return per file (default: 100, configurable via DJANGOMCPMAXLOGLINES env var)
~/Library/Application Support/Claude/claudedesktopconfig.json
The model name (e.g., "Post")
Optional list of fields to order by (e.g., ["-createdat", "title"])
The primary key of the instance
Optional list of check tags (e.g., "models", "compatibility")
The Django topic or feature to search for (e.g., "models", "queryset", "migrations", "authentication")
The URL pattern name (e.g., "postdetail", "admin:index")