Skip to main content
Glama
@cmssy/mcp-server

@cmssy/mcp-server

Official

Bulk update records

bulk_update_records
Destructive

Apply one field, status, or publish change to many records in a single call, targeting IDs or filter matches with validation and pagination.

Instructions

Apply one change (field values, status and/or published) to many records of a model in a single call: the records named by ids, or every record matching filter with allMatching. Each record is validated, audited and announced to webhooks like update_record. Handles up to 200 records per call; a non-null nextCursor means more records match - pass it back with the same arguments to continue. Returns updated, unchanged (records already at the requested status and visibility, with no data to write), failedCount, a sample of failures (id + reason) and nextCursor.

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>"
    },
    "name": "bulk_update_records"
  }
}

Input Schema

NameRequiredDescriptionDefault
idsNoExplicit record ids (from list_records), at most 200
dataNoField values written to every selected record, keyed by the model's field keys and merged like update_record: fields you don't pass are unchanged, and a translatable field takes a language map whose missing languages are kept.
cursorNonextCursor from the previous call, to continue the same run
filterNoSame grammar as list_records: per key scalar equality, $in, $gte/$lte, $regex (literal substring); 'status' filters the record status
statusNoNew status for every selected record (validated against the model's statusField transitions)
publishedNoPublish (true) or unpublish (false) every selected record; an unpublished record stays off every public read until published again
allMatchingNoTarget every record matching filter (all of the model's records when filter is omitted); ignores ids
modelIdOrSlugYesThe model's id or slug (from list_models)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.73.2

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only mark this destructive/non-read-only; the description adds real substance beyond them — each record is validated, audited and announced to webhooks, the per-call cap of 200, and the meaning of a non-null nextCursor. It also discloses the differing treatment of unchanged records and the visibility effect of unpublishing.

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 dense sentences ordered purpose → targeting → side effects → return shape, with no filler. The batching limit and cursor rule are placed where an agent will look before choosing arguments.

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 an 8-parameter mutation with no output schema, the description covers selection modes, the 200-record cap, resumption via cursor, side effects, and the shape of the result including failures and unchanged counts. Nothing material is missing for correct invocation.

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 the baseline would be 3, but the description adds cross-parameter semantics the schema does not spell out: either ids or filter+allMatching, and that cursor must be replayed with identical arguments. It also frames 'one change' per call, which constrains how data/status/published are combined.

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 with exact scope: 'Apply one change (field values, status and/or published) to many records of a model in a single call', plus the two targeting modes. It distinguishes itself from the single-record sibling by naming 'many records' and by comparing behavior to 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?

It clearly explains the two selection modes (explicit ids vs. filter with allMatching) and tells the agent to pass nextCursor back with the same arguments to continue a run. It doesn't state an explicit when-not (e.g. 'use update_record for a single record'), so it stops short of full alternative routing.

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