Skip to main content
Glama
davidharutyunyan

Archicad MCP Connector

by davidharutyunyan
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Get revision changes

get_revision_changes
Read-onlyIdempotent

Retrieve tracked revision changes by document revision, layout, element, or change ID to review what was modified, issued, or archived in an Archicad project.

Instructions

Read-only Change Manager data (changes tracked for revisions, shown by change markers). Give ONE mode (default: every change of the project): documentRevision (changes in one layout revision, GUID from get_revisions), layouts / allLayouts (current revision changes of layouts), elements (changes an element belongs to) or changeIds. Output: {changes: [{id, description, lastModified, modifiedBy, issued, archived, customFields, firstIssue?}], count} | {documentRevision, changes} | {layouts: [{layout: {databaseGuid, id, name}, changes | error}]} | {elements: [{guid, changeIds, changes} | {error}]}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
layoutsNoLayouts: layout database GUID (get_revisions layout.databaseGuid), layout ID, name, or 'ID name'
elementsNoElements whose changes to return
changeIdsNoChange IDs to look up
allLayoutsNoCurrent revision changes of every layout
documentRevisionNoDocument revision GUID (documentRevisions[].guid of get_revisions)
includeFirstIssueNoAlso return the first revision issue each change was issued in (default false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover readOnly/idempotent/non-destructive, but the description adds domain context (what changes represent, that they surface via change markers) and enumerates the return shapes. It doesn't discuss auth needs or volume/rate limits, so not a 5.

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 purpose and the mode-selection rule, then the output contract. Dense with symbols and the long output enumeration costs some readability, but nearly every clause carries distinct 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 6-param, multi-mode tool with no output schema, the description covers mode selection, default behavior, and all four response shapes. Nothing essential for correct invocation 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 coverage is 100%, so baseline is 3, but the description adds meaning by mapping parameters to modes and disclosing the default behavior (no params = every project change) and that exactly one mode should be supplied. It largely mirrors the schema's per-field descriptions beyond that.

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+resource ('Read-only Change Manager data') and immediately clarifies the domain ('changes tracked for revisions, shown by change markers'). The enumerated modes make it distinguishable from the sibling get_revisions, which it references for GUID sourcing.

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?

Explicitly instructs 'Give ONE mode' and labels the default ('every change of the project'), then lists each mode and its trigger. It clearly discriminates mode usage, though it doesn't state when to prefer this tool over the sibling get_revisions beyond sourcing GUIDs.

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