jhipster-mcp has 13 tools with mostly complete schemas and descriptions. Tool names follow verb_noun convention (validate_jdl, create_app_from_jdl, etc.), which is good. However, descriptions vary in quality, some are detailed (create_app_from_jdl: 200+ chars with dryRun explanation), others are terse (add_entity, add_relationship lack detail on what fields are required). Parameter descriptions are present but inconsistent: some params like 'blueprints' and 'extraArgs' are well-documented, others lack context on valid values or constraints. Output schemas are not explicitly documented in the visible code, tool responses are inferred from RunResult/ApplyJdlResult types but not surfaced in tool registration. Error handling is basic: no recovery guidance, no categorization of retryable vs fatal errors. The run_jhipster tool is a generic escape hatch that bypasses safety, high risk. Overall: solid foundation, but descriptions need depth, output schemas need explicit documentation, and error handling needs recovery guidance.
Add a new entity to an existing JHipster project
Add a relationship between entities in an existing JHipster project
Scaffolds a new JHipster application by writing a JDL file to the target directory and running `jhipster jdl <file> --force --skip-git`. The directory should be empty. Pass dryRun=true to preview without writing.
Generate CI/CD configuration for a JHipster project
Generate deployment configuration (Docker Compose or Kubernetes) for a JHipster project
Apply JDL to an existing JHipster project via `jhipster jdl <file> --force --skip-git`
Display JHipster version and configuration information
Preview what a JHipster generator upgrade would change
Output schemas not explicitly documented. Tool responses inferred from TypeScript types (RunResult, ApplyJdlResult) but not surfaced in tool registration. LLMs cannot see what fields to expect from each tool.
Descriptions for add_entity, add_relationship, set_option, generate_ci_cd, generate_deployment, and run_jhipster are under 50 characters and lack actionable context. LLMs cannot determine when to use these tools vs alternatives.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 35 | 2025-06-18+ | v2 |
List available JHipster commands for a project
Run arbitrary JHipster CLI commands
Set JHipster options on entities in an existing project
Check for available JHipster generator upgrades
Validate JDL syntax and semantics via `jhipster jdl --dry-run`
run_jhipster is a generic escape hatch that accepts arbitrary CLI arguments. No validation, no safety guardrails, no error recovery guidance. High risk for agent misuse.
Error handling is minimal. No recovery guidance (e.g., 'Try search_users() first'), no error categorization (retryable vs fatal), no actionable error messages. Agents cannot self-correct on failures.
Parameter descriptions inconsistent. Some params (blueprints, extraArgs) are well-documented; others (entity name in add_entity, relationship type in add_relationship) lack detail on valid values, constraints, or format.