Skip to main content
Glama
@cmssy/mcp-server

@cmssy/mcp-server

Official

Create record

create_record

Add a record to a data model by passing its model ID or slug and field-keyed data, including product records with stock. Use it to create CMS entries and get the record's live storefront URL.

Instructions

Add a record (entry) to a data model. Pass the model id or slug and a data object whose keys are the model's field keys (use get_model first if unsure). A product is a record too: pass a model whose product capability is enabled (get_model shows product.enabled), and list_products then lists it with its stock. Each record carries url: its live storefront link, built by the server from the model's urlPattern and the site's public site URL. Use it whenever you link to a record and never build a storefront URL yourself (not from a slug, not from the site address). When url is null or missing, say why instead of guessing: the model has no urlPattern (set it with update_model), the model is not delivered (deliveryAccess none, or it is the login model), the site has no public site URL, or the record - or one it links to - is unpublished.

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": {
      "modelIdOrSlug": "<modelIdOrSlug>",
      "data": "<data>"
    },
    "name": "create_record"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataYesField values keyed by the model's field keys. A translatable field (localized: true on the model) takes a language map, e.g. { title: { en: 'Ball bearing', pl: 'Łożysko' } }
publishedNoWhether the record goes live on the site and delivery API (default true). false creates it hidden from every public read until published; the workspace draft secret still previews it.
modelIdOrSlugYesThe target model's id or slug (from list_models)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.73.2
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / published
      Added value: +{
      +  "description": "Whether the record goes live on the site and delivery API (default true). false creates it hidden from every public read until published; the workspace draft secret still previews it.",
      +  "type": "boolean"
      +}
    • addedInput schema / required
      Added value: +[
      +  "modelIdOrSlug",
      +  "data"
      +]
  2. First observedv0.73.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false and destructiveHint=false, so they add little beyond "this is a write". The description adds real context: that the server synthesizes `url` rather than the caller, and an enumerated set of reasons `url` can be null with the remedy for each. It does not cover error behavior or what the remaining response payload contains.

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?

Front-loaded with the action and required inputs, then moves to the secondary `url` guidance; every section has a purpose. Slight redundancy in the emphatic restatement "never build a storefront URL yourself (not from a slug, not from the site address)", and the `url` discussion occupies roughly half the text for a field that is not a parameter.

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?

With no output schema, the description usefully explains the one response field that matters most (`url`) and why it may be absent, which is exactly what an agent needs when linking after creation. It remains silent on failure modes and permission requirements, and the bulk of `published` semantics lives in the schema rather than the description.

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 100%, including the localized-language-map convention for `data` and the draft-preview semantics of `published`, so the schema already carries the parameter burden. The description reinforces that `data` keys are the model's field keys and points to get_model, but adds no syntax or format detail beyond the schema. Baseline 3 applies.

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

Purpose4/5

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

States a specific verb and resource: "Add a record (entry) to a data model", and then clarifies a non-obvious conceptual point that a product is also a record, which prevents an agent from looking for a separate product-creation tool. It names get_model as the prerequisite lookup and list_products as the downstream read, giving partial sibling differentiation, but does not explicitly contrast with update_record.

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 concrete when-to-use context: call get_model first if the field keys are unknown, and use a model with product capability enabled when creating a product. It also gives a strong directive about linking ("never build a storefront URL yourself"). It stops short of explicit when-not-to-use or exclusions versus update_record/bulk_update_records.

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

Deploy Server

Other Tools