Skip to main content
Glama
hostinger

hostinger-api-mcp

Official
by hostinger
OverviewSchemaSourceRelated ServersDiscussions(1)Admin
TypeScript
Remote

Create website

horizons_createWebsiteV1

Create a new website from a detailed project specification using Hostinger Horizons. The tool returns a website URL and ID, while the site is generated asynchronously and ready in a few minutes.

Instructions

Create new Hostinger Horizons website from the given message.\n Use this tool when user asks you to create a website, landing page, blog or any other type of application.\n This tool initiates the website creation process and returns a website URL and ID. The generation happens asynchronously.\n After invoking this tool, your chat reply must be EXACTLY 1 sentence summarizing that Hostinger Horizons is now creating their website and it will be ready in a few minutes and you should provide the website URL to the user immediately Do not write code.\n\nTo edit afterwards, use the Edit website tool with the returned website ID, or the user can go to Hostinger Horizons interface in the provided website URL. If the tool call fails with an error, you should provide a clear explanation of the error and do not generate code yourself in the chat. \n TECHNOLOGY STACK CONSTRAINTS (STRICTLY ENFORCED):\n The environment is limited to the following technologies. You MUST NOT use, suggest, or implement any technology outside this list:\n \n

  • Language: JavaScript ONLY.

  • Languages like TypeScript, Rust, Python, Java, PHP, etc., are STRICTLY PROHIBITED.\n

  • Framework: React.\n

  • Navigation: React Router.\n

  • Styling: TailwindCSS.\n

  • Components: shadcn/ui (built with @radix-ui primitives).\n

  • Icons: Lucide React.\n

  • Animations: Framer Motion.\n \n BACKEND & DATA STORAGE:\n

  • Horizons integrated backend is the EXCLUSIVE solution for persistent data storage, authentication, and database needs.\n

  • Local databases (SQLite, MySQL, etc.) are STRICTLY PROHIBITED.\n

  • Third-party services (Firebase, AWS Amplify) are allowed ONLY if explicitly requested by the user.\n \n MAPS:\n

  • OpenStreetMap is the default provider.\n

  • Alternative providers (Google Maps, Mapbox) are allowed ONLY if explicitly requested by the user.\n

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
messageYesmessage parameter

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.5.0
  2. Removedv1.2.1
  3. Addedv0.2.14

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With annotations only declaring readOnlyHint=false and destructiveHint=false, the description carries substantial behavioral weight. It discloses asynchronous generation, URL and ID return values, the exact 1-sentence chat reply requirement, the prohibition on writing code, error-handling guidance, and strict technology-stack constraints. No contradiction with annotations exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose, use case, async behavior, and return values, then organizes constraints into clear labeled sections. It is long, but nearly every sentence carries actionable guidance for the agent, including post-call reply format and tech-stack limits.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, yet the description states what the tool returns (URL and ID), explains that generation is asynchronous, defines the expected chat reply, gives failure handling, and routes future edits to the correct sibling. This is sufficient for an agent to invoke the tool and handle the outcome correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the `text` field inside `message` already has a detailed specification. The tool description only says 'from the given message,' adding no semantic value beyond the schema. This meets the baseline for high schema coverage but does not elevate it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Create new Hostinger Horizons website from the given message.' It clearly enumerates triggering use cases (website, landing page, blog, application) and distinguishes itself from edit/clone siblings by emphasizing 'new' and explicitly pointing to the `Edit website` tool for subsequent edits.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says 'Use this tool when user asks you to create a website, landing page, blog or any other type of application,' giving clear trigger conditions. It also points to `Edit website` for later modifications and instructs what to do on failure, though it does not explicitly enumerate exclusions like 'do not use for editing existing sites.'

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools