Loading ToolBench
Model Context Protocol server for Netlify platform integration, providing tools for site management, deployments, team operations, extensions, and project configuration
Critical failures across naming, descriptions, and schemas. Tool names lack action verbs and are overly generic (e.g., 'netlify-user-services', 'netlify-deploy-services'). Descriptions are vague and do not explain WHEN to use each tool or what distinguishes them. Input schemas are severely underspecified: most tools use a generic 'selectSchema' object with an 'operation' enum and untyped 'params' object, providing zero guidance on what parameters each operation accepts. No output schemas documented. Error handling absent. This server violates foundational tool design patterns.
ALWAYS call when writing code. Required step before creating or editing any type of functions, Netlify sdk/library usage, etc. Use other operations for project management.
ALWAYS call when writing serverless or Netlify code. required step before creating or editing any type of functions, Netlify sdk/library usage, etc.
Select and run one of the following Netlify operations get-deploy, get-deploy-for-site, deploy-site, deploy-site
Select and run one of the following Netlify operations change-extension-installation, get-extensions, get-full-extension-details, initialize-database
Select and run one of the following Netlify operations get-project, get-projects, update-visitor-access-controls, update-forms, get-forms-for-project, manage-form-submissions, update-project-name, manage-env-vars, create-new-project
Select and run one of the following Netlify operations get-teams, get-team
Tool names lack action verbs and are generic service aggregators. 'netlify-user-services', 'netlify-deploy-services' do not convey what action occurs. LLMs cannot infer intent from names alone. Should be 'get_user', 'deploy_site', 'get_deploy', etc.
Input schemas are severely underspecified. All multi-operation tools use a generic 'selectSchema' object with an untyped 'params' object. No documentation of what parameters each operation (e.g., 'get-deploy', 'deploy-site') accepts, their types, or constraints. LLMs cannot determine valid inputs.
Inferred effective spec: 2026-07-28+.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 18 | 2026-07-28+ | v2 |
Select and run one of the following Netlify operations get-user
Descriptions are vague and do not explain WHEN to use each tool or what distinguishes similar tools. 'Select and run one of the following Netlify operations...' does not guide LLM selection. No indication of prerequisites, return types, or side effects (e.g., which operations are destructive).
No output schemas documented. LLMs cannot plan downstream tool calls or extract required fields (e.g., deploy_id, site_id) for chaining. Responses are opaque.
No error handling guidance. No indication of retryable vs. fatal errors, no recovery suggestions, no actionable error messages. Agents cannot self-correct on failures.