Skip to main content
Glama
@cmssy/mcp-server

@cmssy/mcp-server

Official

Import records

import_records
Destructive

Bulk-import up to 1000 rows into a data model, creating records or updating existing ones through an upsert key so repeated syncs do not duplicate data. Returns per-row ids and errors.

Instructions

Bulk-import records into a data model (up to 1000 rows). Without upsertKey each row CREATES a record; with upsertKey (a unique field or the product SKU field) a row matching an existing record UPDATES it instead, so a repeated sync does not duplicate. A translatable field takes a language map ({ title: { en: '...', no: '...' } }); a language the workspace has not enabled is rejected. Returns importedCount (created), updatedCount, per-row errors, and per-row record ids with CREATED / UPDATED / UNCHANGED.

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>",
      "rows": "<rows>"
    },
    "name": "import_records"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsYesArray of plain objects 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', no: 'Kulelager' } }. Without upsertKey each row creates a record, so every language the row should have must be in it. A row matched through upsertKey is merged into the existing record: only the keys the row carries change.
upsertKeyNoA key from the model's uniqueFields, or its product skuField. A row whose value matches an existing record updates that record; any other row is created, so re-running the same file does not duplicate it. Every row must carry the key. Not allowed on member (auth) models.
modelIdOrSlugYesTarget model id or slug

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.73.2
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / required
      Added value: +[
      +  "modelIdOrSlug",
      +  "rows"
      +]
  2. First observedv0.73.1

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already flag readOnlyHint=false and destructiveHint=true, so the write/destructive profile is known. The description meaningfully adds that a matched row is merged (only carried keys change), that a repeated sync is idempotent, and that a non-enabled language is rejected — real behavior beyond the annotations, though it omits auth/permission constraints on the target model.

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

Conciseness5/5

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

Four sentences, front-loaded with scope and capacity, then the create-vs-upsert decision, then the field-format exception, then the return shape. Every sentence carries information; no boilerplate.

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?

No output schema exists, yet the description enumerates the returned fields (importedCount, updatedCount, per-row errors, per-row ids with CREATED/UPDATED/UNCHANGED). Combined with the 1000-row limit and upsert semantics, an agent has everything needed to call it correctly.

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 100%, so baseline is 3, and the description adds genuine semantics on top: upsertKey is a unique field or the product SKU field and must appear on every row, plus the language-map rejection rule that the schema does not mention.

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 ("Bulk-import records into a data model"), including a hard capacity limit (up to 1000 rows), which immediately separates it from single-record tools like create_record and from bulk_update_records.

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 when-to-use logic for the two modes: without upsertKey each row creates, with upsertKey matching rows update instead, so a repeated sync does not duplicate. It does not name a sibling alternative or state when to prefer bulk_update_records/bulk_delete over this tool, so it stops short of a 5.

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