Laya
Laya multilingual reads a text and typed questions, then chooses one of the answers you listed for each question. CPU only. The call returns the decision in the same response.
Service id: laya
Version: 0.1.0
Status: available
Canonical payloads: https://mcp.glc-rag.hu/guide/laya/payload · markdown · docs://laya/payload
Authentication
MCP endpoint: https://mcp.glc-rag.hu/mcp (streamable HTTP)
Agents (recommended): self-register with account_type=agent to get an
auto-approved token — see https://mcp.glc-rag.hu/guide/agent.
Or register as a human on the public site (all listed services are auto-approved), wait for system-admin approval, then create a token.
Authorization: Bearer mcp_...
Cursor mcp.json example:
{
"mcpServers": {
"laya": {
"url": "https://mcp.glc-rag.hu/mcp",
"headers": {
"Authorization": "Bearer mcp_YOUR_TOKEN"
}
}
}
}
Tools
laya_status
Whether the Laya multilingual checkpoint is loaded, plus the CPU thread budget. Free — 0 credits.
Input schema:
{
"type": "object",
"properties": {},
"additionalProperties": false
}
Examples:
{}
laya_decide — Decide
Pick one allowed answer per question. Pass text and questions (each with id, question, and options). 1 credit per 10 questions, rounded up. Same call returns the choices.
Input schema:
{
"type": "object",
"additionalProperties": false,
"required": [
"text",
"questions"
],
"properties": {
"text": {
"type": "string",
"minLength": 1,
"maxLength": 40000,
"description": "Text the questions are about"
},
"questions": {
"type": "array",
"minItems": 1,
"maxItems": 32,
"description": "Questions and the answers the model may pick",
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"id",
"question",
"options"
],
"properties": {
"id": {
"type": "string",
"minLength": 1,
"maxLength": 64
},
"question": {
"type": "string",
"minLength": 1,
"maxLength": 500
},
"options": {
"type": "array",
"minItems": 2,
"maxItems": 64,
"uniqueItems": true,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 200
}
}
}
}
}
}
}
Examples:
{
"text": "J\u00f3 napot! A m\u00falt heti rendel\u00e9sem (R-1842) m\u00e9g mindig nem \u00e9rkezett meg, holnapra viszont m\u00e1r kellene. K\u00e9rem, n\u00e9zz\u00e9k meg, mi t\u00f6rt\u00e9nt, \u00e9s ha lehet, k\u00fcldj\u00e9k ki m\u00e9g ma.",
"questions": [
{
"id": "tema",
"question": "Mir\u0151l sz\u00f3l a lev\u00e9l?",
"options": [
"sz\u00e1ll\u00edt\u00e1s",
"sz\u00e1mla",
"\u00faj aj\u00e1nlat",
"egy\u00e9b"
]
},
{
"id": "surgosseg",
"question": "Mennyire s\u00fcrg\u0151s?",
"options": [
"r\u00e1\u00e9r",
"hamarosan",
"ma kell"
]
}
]
}
Usage notes
Call laya_decide with text and questions. Each question has id, question, and options (the allowed answers). The response answers list has one row per question: answer is one of that question’s options, scores is the probability of each option, confidence is the model’s confidence in the pick.
Billing: 1 credit per 10 questions, rounded up (1–10 costs 1, 11–20 costs 2). laya_status is free. A failed call is not billed.
The checkpoint is convaiinnovations/laya-multilingual on CPU. It uses every core except 4, and reads up to 8192 tokens (model ceiling; put the decisive part first). At most 32 questions and 64 options per question.
Errors / limits
Missing text, duplicate ids or options, or a model failure → {error, is_error}. Those calls cost 0 credits.
Agent discovery
- Agent registration:
https://mcp.glc-rag.hu/guide/agent - Markdown:
https://mcp.glc-rag.hu/guide/laya.md - Index:
https://mcp.glc-rag.hu/llms.txt - MCP resource:
docs://laya