Skip to main content
Glama

create_service

Creates a new hosted service for a 24/7 bot, setting runtime, port, size, database, and public access before you upload code.

Instructions

Yeni bir servis oluşturur (kod henüz yüklenmez — ardından deploy_service). Ayarlar kodun kökündeki etrink.json ile de verilebilir: {"runtime":"python|node|static|binary","version":"node: 26|24|22 · python: 3.14|3.13|3.12|3.11 (isteğe bağlı; yoksa package.json engines.node / .python-version, o da yoksa en yeni)","start":"python main.py","port":8080,"size":"small|medium|large","db":"none|postgres|postgres_redis","public":false,"spa":false}. static = kökte index.html olan HTML/CSS/JS sitesi (sunucu kodu yok, port 8080 ve HTTPS otomatik; spa:true bilinmeyen yolları index.html'e düşürür). GÜVENLİK KURALI (geçersiz kılınamaz): desteği bitmiş dil sürümü istenirse yükleme reddedilir (version_eol); derlemede npm audit (yüksek/kritik) ya da pip-audit (düzeltmesi olan açık) bulursa derleme başarısız olur — paketleri güncel sürüme yükseltip tekrar yükle. Boyutlar: small 0.25 CPU/256 MB/1 GB disk, medium 0.5/512 MB/3 GB, large 1/1 GB/10 GB. Ücret (kullandıkça öde müşterisi): günlük karşılığı small $0.10, medium $0.20, large $0.40, +postgres $0.10, +postgres_redis $0.13; başlamış her saat bakiyeden kesilir (aynı gün silinirse yalnız kullanılan saatler). Oluşturma/yükleme için en az 1 günlük bakiye gerekir (insufficient_balance).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>"
    },
    "name": "create_service"
  }
}

Input Schema

NameRequiredDescriptionDefault
dbNoServise özel veritabanı: DATABASE_URL / REDIS_URL otomatik verilir
nameYesGörünen ad, ör. 'Binance sinyal botu'
portNoServis HTTP dinliyorsa portu (PORT env olarak da verilir)
sizeNo
slugNoAdres adı (a-z0-9-, 3-30). Boşsa addan üretilir
regionNoLokasyon (list_services yanıtındaki regions)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so: it discloses that this is a mutation with billing consequences (hourly deduction from balance, only used hours charged if deleted same day), per-tier price deltas, and size resource specs. It also states non-overridable validation behavior (EOL runtime rejected with version_eol; builds fail on npm audit high/critical or pip-audit findings) and that static sites auto-bind port 8080 with HTTPS.

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

Conciseness3/5

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

The purpose is front-loaded in the first sentence, but the body is a single dense paragraph with an inline JSON schema blob that is hard to parse. Some content is duplicated (size tiers appear both inside the etrink.json illustration and again in "Boyutlar"), which dilutes scanability even though most sentences do carry useful information.

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

Completeness4/5

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

For an unannotated creation tool with billing and security constraints and no output schema, the description is unusually complete: prerequisites, cost model, validation failure modes and config-file alternative are all covered. What is missing is only what is returned on success (the created service record/slug) and whether name/slug must be unique.

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 coverage is already 83%, but the description adds meaning the schema lacks: it expands the size enum into concrete CPU/RAM/disk tiers with prices, prices the db enum options (+$0.10 postgres, +$0.13 postgres_redis), and explains that settings can alternatively be supplied via a root etrink.json with runtime/version/start/port/public/spa keys that are not even present as tool parameters. Remaining gap is that slug uniqueness and region sourcing (list_services regions) are only hinted at.

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 first clause names a specific verb and resource ("Yeni bir servis oluşturur") and immediately disambiguates it from the sibling step by stating that code is not uploaded here, pointing to deploy_service as the follow-up. An agent can tell create_service apart from deploy_service, update_service or get_service without opening any schema.

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 create-then-deploy_service ordering is explicit, and a hard prerequisite is given ("Oluşturma/yükleme için en az 1 günlük bakiye gerekir") with the failure code insufficient_balance. It does not name conditions that would instead call for update_service on an existing service or list_services first (e.g. to fetch valid regions/slugs), so no explicit when-not guidance.

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