RPG Maker MZ Authoring MCP

Overview Schema Source Related Servers Discussions Admin

database edit collection

database_edit_collection

Edit nested RPG Maker MZ database collections such as traits, effects, and actions using typed add, update, remove, or move operations. Preview first and set apply=true to commit a clean change set.

Instructions

Edit a nested collection (traits, effects, learnings, actions, dropItems, members, flashTimings, soundTimings) with typed ops: {op:"add", entry, index?} | {op:"update", index, entry (partial), fingerprint?} | {op:"remove", index, fingerprint?} | {op:"move", from, to}. update/remove/move need expectedRevision (collections..revision from database_get_record). Trait/effect codes and dataIds accept labels (e.g. code "State Resist", dataId "Poison").

Preview-first: returns a change set (normalized + native diff, validation incl. reverse references). Pass apply=true to commit immediately when the preview is clean.

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": {
      "category": "<category>",
      "id": "<id>",
      "collection": "<collection>",
      "ops": "<ops>"
    },
    "name": "database_edit_collection"
  }
}

Input Schema

Name	Required	Description
`id`	Yes
`ops`	Yes
`apply`	No	Commit right after a successful preview (non-destructive operations only; needs --allow-write; warnings also need acknowledgeWarnings). Default false = preview only.
`category`	Yes	Database category
`collection`	Yes
`allowScript`	No	true ONLY if the user explicitly asked to insert JavaScript (script commands, script conditions/operands, route scripts).
`description`	No	Optional description stored in the transaction log
`expectedRevision`	No
`acknowledgeWarnings`	No	Accept validation warnings when apply=true. Review them with the user first.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 14, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Annotations only declare the read/write and idempotency profile; the description adds substantial behavior beyond them: preview-first default with a returned change set containing normalized and native diffs, validation including reverse references, an optimistic-concurrency requirement via expectedRevision, and label-tolerant trait/effect codes and dataIds. That is exactly the context an agent needs before committing a mutation.

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 the collection keys, then the op grammar, then the preview/apply contract — a sensible order with no filler sentences. The parenthetical density and inline grammar make it slightly harder to scan than it needs to be.

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?

For a 9-parameter mutation tool with no output schema, the description does the important work: it describes the returned change set and the preview/commit duality. Remaining gaps are the meaning of category/collection selection and how this tool relates to the preview_changes/apply_changes siblings.

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?

With schema coverage at 56% and an untyped ops array (additionalProperties only), the description carries the critical load by spelling out the four op shapes with their required and optional fields. It also explains expectedRevision's source and the apply=true commit gate, but leaves category, id, collection, and the transaction-log 'description' parameter to the schema.

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 ('Edit a nested collection') and enumerates the exact collection keys in scope (traits, effects, learnings, actions, dropItems, members, flashTimings, soundTimings), which is far more specific than a generic 'update record'. It never names database_update_record, so the boundary between editing a nested collection and editing scalar record fields is left to inference.

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 a clear operating workflow: preview by default, pass apply=true to commit 'when the preview is clean', and update/remove/move require expectedRevision sourced from database_get_record's collections.<key>.revision. It does not say when to prefer this over siblings like database_update_record, database_apply_changes, or database_preview_changes, nor what to do when the preview is not clean.

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

Deploy Server