Skip to main content
Glama
Sign In

Komers Sites

by my.udx.app
OverviewDiscussionsAdmin

Site settings

set_site_settings

Change site settings.

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": {
      "site": "<site>"
    },
    "name": "set_site_settings"
  }
}

Input Schema

NameRequiredDescriptionDefault
faqNoQuestions customers ask and the answers, published as FAQPage schema on the home page and in llms.txt so AI assistants answer them from the site. Use the owner's real answers (opening hours, halal status, delivery, parking, payment methods). Replaces the whole list; [] clears it.
siteYesSite slug (e.g. "kopitiam-muar") or id
linksNoThe business's other official web presences — its main/old domain, LinkedIn, Facebook, Instagram, Google Business profile. Published as schema.org sameAs (and in llms.txt and the agent manifest) so search and AI engines connect this site to the brand's existing entity instead of treating it as a stranger. Replaces the whole list; [] clears it.
titleNo
reviewsNoCustomer reviews: submitted at POST /_k/reviews (or by a customer's agent), approved reviews become AggregateRating and Review schema on product pages and the business entity.
businessNoThe site owner's business: name, public contact email, phone, address, SSM/registration no. Shown on the site's /privacy page and used as the sender name and reply-to of emails to visitors. Empty string clears a field.
og_imageNoImage for link previews: a site path like "img/hero.jpg" or an https URL
analyticsNoCookie-free page view counting
ai_trainingNoWhether AI model training crawlers (GPTBot, CCBot, Google-Extended, …) may read the site (default true). false blocks them in robots.txt; AI assistants and AI search (ChatGPT, Claude, Perplexity) can still read and cite the site. Only change it when the owner asks.
descriptionNoShort description for search engines and link previews
notify_emailNoWhere form notifications go (defaults to the account email)
visitor_signinNoVisitor sign-in by emailed code: "off", "open" (anyone can sign up) or "invite" (only emails added with invite_visitor)
agent_transactionsNoLet AI agents start transactions through the site's public MCP endpoint (default false): request_booking returns a secure confirmation link the visitor clicks to book, start_checkout returns the Komers payment link. The visitor always completes the transaction themselves. Ask the owner before turning it on.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

C2.4/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is known. Beyond that the description contributes nothing: it does not disclose that this is a partial update (only the site slug is required), that array fields like faq and links replace the whole list, or that empty strings clear fields — all behaviors buried in the schema rather than surfaced here.

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

Conciseness2/5

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

Three words is not conciseness but absence of specification. For a thirteen-parameter mutation tool with nested objects, this leaves the caller with no front-loaded orientation before parsing a large schema.

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

Completeness2/5

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

A partially-updating mutation tool with nested objects, an enum, and no output schema requires the description to establish update semantics, scope of changes, and any confirmation requirements. The rich schema compensates for field-level detail, but nothing tells the agent whether omitted fields are preserved or reset, or what the tool returns after a change.

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 92%, so the schema itself explains all thirteen parameters in depth, and the baseline of 3 applies. The description adds no parameter meaning whatsoever, which is acceptable given coverage but earns no credit.

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

Purpose3/5

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

"Change site settings" states a mutation verb and a resource, but "settings" is a grab-bag covering thirteen unrelated fields (FAQ, links, reviews, analytics, AI training). Nothing distinguishes it from siblings like set_booking, set_shop, or set_site_komers_store, so an agent cannot tell which set_* tool owns which configuration surface from the description alone.

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

Usage Guidelines2/5

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

No when-to-use guidance, no prerequisites, and no pointer to get_site for reading current values or to the sibling set_* tools for adjacent settings. The only conditional advice ("Only change it when the owner asks", "Ask the owner before turning it on") lives inside two parameter descriptions, not in the tool description where selection decisions are made.

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

All Komers Sites toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources