Skip to main content
Glama

Lokand Restaurant MCP

Create restaurant

create_restaurant

Create a new Lokand restaurant on a customer's behalf — ONE call can produce a complete LIVE website when you pass menu (and optionally hours/theme). Returns working OAuth tokens (Bearer, for follow-up edit ops), the live site_url, and a claim_url. NEXT STEPS after this call: refine with add_item/update_item/set_theme if needed, then give the customer the claim_url so they take ownership (free signup); poll claim_status to keep access after they claim. Requires a client registered once via POST /api/auth/oauth2/register (see https://lokand.com/auth.md).

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": {
      "client_id": "<client_id>",
      "client_secret": "<client_secret>",
      "name": "<name>"
    },
    "name": "create_restaurant"
  }
}

Input Schema

NameRequiredDescriptionDefault
menuNoThe full menu, inline — pass this to go live in one call instead of separate create_menu/add_category/add_item calls
nameYesRestaurant name
slugNoOptional site slug (<slug>.lokand.co); generated from the name when omitted. If taken, a suffixed variant is used automatically.
hoursNoOpening hours keyed mon..sun, each {"open":"10:30","close":"22:00"} or {"closed":true}
placeNoWhere the business is and what kind of place it is: lat/lng; address {streetAddress, addressLocality (district), addressRegion (city or province), postalCode, addressCountry (ISO 3166-1 alpha-2)}; timezone (IANA, e.g. "Europe/Istanbul"); category (e.g. restaurant, cafe, bakery, bar, meyhane, fast_food, dessert_shop); up to 6 cuisines (e.g. turkish, kebab, seafood, sushi, vegan). Merged into what is stored: keys you pass replace, keys you leave out stay.
themeNo
publishNoPut the site live immediately (default true). Pass false to keep it a draft.
maps_urlNoA Google Maps, Apple Maps, Yandex or OpenStreetMap link (short share links work), or a "lat, lng" pair. Sets the coordinates.
client_idYesRegistered OAuth client id
descriptionNo
contact_infoNoContact info: phone, email, address, instagram
client_secretYesThe client's secret
currency_codeNoISO currency for menu prices, e.g. "USD"
customer_emailNoCustomer's email: binds the claim to it and sends them the claim link

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare this is a non-read-only, non-idempotent, open-world write, so the safety profile is covered. The description adds genuinely new behavior: the return payload (Bearer tokens, site_url, claim_url), the ownership/claim lifecycle and the access-loss risk if claim_status is not polled, and a registration prerequisite with a documentation URL. It does not mention that repeated calls create duplicate restaurants, which is the one thing idempotentHint=false implies but never states.

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 opening clause front-loads the core action and the go-live capability, then moves to returns, then to next steps, then to the auth prerequisite — a logical order with no filler. It is dense and slightly overloaded with an inline URL and multiple follow-up commands, but every sentence carries actionable information.

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?

For a 14-parameter, deeply nested mutation tool with no output schema, the description covers the three things an agent cannot infer: what comes back (tokens, site_url, claim_url), what to do after the call, and the one-time OAuth client registration requirement. Nothing essential to invoking it correctly is missing.

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 86%, so the baseline is 3 and the schema already carries most parameter meaning. The description still adds decision-level semantics the schema can't: that `menu` is what converts a bare create into a live site in a single call, and that hours/theme are optional add-ons. It does not clarify the interplay between `publish: false` and the returned site_url, which would have made it a 5.

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?

States a specific verb and resource ("Create a new Lokand restaurant on a customer's behalf") and immediately scopes what the call can accomplish (a complete LIVE website when `menu` is passed). It distinguishes itself from the sibling refinement tools by naming add_item/update_item/set_theme as post-creation steps, and from the granular menu tools by framing the alternative as "separate create_menu/add_category/add_item calls."

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?

Gives explicit sequencing guidance: call this first, then refine with add_item/update_item/set_theme, then hand over the claim_url and poll claim_status. The condition for the one-call go-live path ("when you pass `menu`") is spelled out. It stops short of contrasting with other creation-shaped siblings such as create_full_menu or make_menu_only, so an agent choosing among creation entry points still has a gap.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources