Skip to main content
Glama
lindoai

mcp-lindoai

Official

create_website

Create a website using AI from a text description. Optionally assign to a client by ID or email, or create a new client.

Instructions

Create a new website using AI. Optionally assign to a client by providing client_id (existing) or client_email (lookup or create new).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesDescribe the website to create
schedule_atNoOptional ISO 8601 datetime to schedule for later
client_idNoExisting client ID to assign the website to
client_emailNoClient email. Looks up existing client or creates a new one.
client_nameNoClient name, used when creating a new client with client_email.

Implementation Reference

  • The handler function that executes the 'create_website' tool logic. It builds a request body with prompt and optional scheduling/client fields, then calls the API endpoint /v1/ai/workspace/website via POST.
    async ({ prompt, schedule_at, client_id, client_email, client_name }) => {
      const body = { prompt };
      if (schedule_at) body.schedule_at = schedule_at;
      if (client_id || client_email) {
        body.client = {};
        if (client_id) body.client.client_id = client_id;
        if (client_email) body.client.email = client_email;
        if (client_name) body.client.name = client_name;
      }
      const data = await apiCall("/v1/ai/workspace/website", "POST", body);
      return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] };
    }
  • Zod schema definitions for the create_website tool inputs. Fields: prompt (required string), schedule_at (optional ISO datetime), client_id (optional string), client_email (optional string), client_name (optional string).
      prompt: z.string().describe("Describe the website to create"),
      schedule_at: z.string().optional().describe("Optional ISO 8601 datetime to schedule for later"),
      client_id: z.string().optional().describe("Existing client ID to assign the website to"),
      client_email: z.string().optional().describe("Client email. Looks up existing client or creates a new one."),
      client_name: z.string().optional().describe("Client name, used when creating a new client with client_email."),
    },
  • Registration of the 'create_website' tool on the MCP server via server.tool(), including description, options (title, readOnlyHint, destructiveHint, openWorldHint), and the handler.
    server.tool(
      "create_website",
      "Create a new website using AI. Optionally assign to a client by providing client_id (existing) or client_email (lookup or create new).",
      {
        prompt: z.string().describe("Describe the website to create"),
        schedule_at: z.string().optional().describe("Optional ISO 8601 datetime to schedule for later"),
        client_id: z.string().optional().describe("Existing client ID to assign the website to"),
        client_email: z.string().optional().describe("Client email. Looks up existing client or creates a new one."),
        client_name: z.string().optional().describe("Client name, used when creating a new client with client_email."),
      },
      { title: "Create Website", readOnlyHint: false, destructiveHint: false, openWorldHint: true },
      async ({ prompt, schedule_at, client_id, client_email, client_name }) => {
        const body = { prompt };
        if (schedule_at) body.schedule_at = schedule_at;
        if (client_id || client_email) {
          body.client = {};
          if (client_id) body.client.client_id = client_id;
          if (client_email) body.client.email = client_email;
          if (client_name) body.client.name = client_name;
        }
        const data = await apiCall("/v1/ai/workspace/website", "POST", body);
        return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] };
      }
    );
  • The apiCall helper function used by the create_website handler to make HTTP requests to the Lindo AI API.
    async function apiCall(path, method, body) {
      const url = `${BASE_URL}${path}`;
      const res = await fetch(url, {
        method,
        headers: {
          Authorization: `Bearer ${API_KEY}`,
          "Content-Type": "application/json",
        },
        ...(body ? { body: JSON.stringify(body) } : {}),
      });
      return res.json();
    }
Behavior4/5

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

Annotations already indicate readOnlyHint=false and destructiveHint=false. The description adds that the tool uses AI (openWorldHint consistent) and can create a new client via client_email, which is a side effect beyond the schema.

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

Conciseness5/5

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

The description is two sentences, front-loading the main action. Every part is necessary: creation with AI, and optional client assignment with two methods. No unnecessary words.

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

Completeness3/5

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

The description covers creation and client assignment but lacks output details (what is returned) and prerequisites like authentication. Given no output schema, the description should mention return value.

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

Parameters4/5

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

Schema description coverage is 100%, but the description adds value by explaining the relationship between client_id, client_email, and client_name, clarifying the optional assignment logic beyond individual parameter descriptions.

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 clearly states 'Create a new website using AI' with a verb and resource, and explains optional client assignment. It distinguishes itself from siblings like create_blog or assign_website by combining creation with optional assignment.

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?

The description implies when to use (creating a website, optionally with client assignment) but does not explicitly exclude alternatives like assign_website for assigning existing websites. It provides clear context for client assignment options.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/lindoai/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server