Skip to main content
Glama
anananaTERRA

mcp-indesign-agent

by anananaTERRA

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
INDESIGN_BRIDGENoBridge type to use (e.g., 'applescript'). Default: 'applescript'.applescript
INDESIGN_APP_NAMENoThe name of the InDesign application (e.g., 'Adobe InDesign 2026'). Defaults to the highest version found in /Applications.
INDESIGN_TEMP_DIRNoTemporary directory for the MCP server. Default: tmpdir/mcp-indesign-agent.tmpdir/mcp-indesign-agent
INDESIGN_SCRIPT_TIMEOUT_SECNoTimeout in seconds for InDesign script execution. Default: '300'.300

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
ping_indesignA

Check if Adobe InDesign is reachable (app open, version, active document). Call first in a session before scan_document.

scan_documentA

Scan the active InDesign document into the session Document Model cache and write stable mcp: labels. Call ONCE per session before planning edits; then use execute_batch (not repeated scans).

refresh_documentA

Invalidate and reload the Document Model from InDesign. Use only after manual edits in InDesign or when the cache may be stale — not before every mutation.

get_document_modelA

Return a summary of the cached Document Model without rescanning InDesign (unless forceRefresh or cache empty).

get_selectionB

Read the current InDesign selection as stable UUIDs and sync them into the session cache.

analyze_pageA

Classify page items into semantic roles (Header, Subtitle, Body, Caption, Image, Background, Logo, Decorative, Unknown) and store them on the Document Model. Call after scan_document so batch targets like {role:"Header"} work. Typical flow: scan → analyze_page → execute_batch → summarize_changes.

snapshotA

Capture or inspect Document Model snapshots. Modes: before | after | list | diff. Capture uses the current session cache (run scan_document first).

summarize_changesA

Diff snapshot before vs after into agent-readable summary. Call after execute_batch (or layout_assistant fix). Defaults to the last before/after pair from scan_document + batch.

preview_batchA

Dry-run a batch against the cached Document Model (no InDesign writes). Call after scan_document. Prefer preview_batch before a large execute_batch.

execute_batchA

Preferred mutation path: resolve targets → checkpoint gate → one dispatcher round-trip inside a single ENTIRE_SCRIPT undo transaction → modelPatch on cache. ALWAYS prefer this over execute_operation / layout_operation when combining ops. Mutating batches need an on-disk checkpoint for the current generation; the server takes one automatically and refuses the batch if saving it fails. Typical flow: scan_document → (analyze_page) → execute_batch → summarize_changes.

execute_operationA

Thin single-op wrapper around execute_batch (checkpoint/move/resize/delete/duplicate/setText/replaceText/setFont/setFill/applyStyle). op=checkpoint saves an .indd copy to _checkpoints/ next to the document and needs no target — run it before a risky sequence of edits. Prefer execute_batch when issuing two or more ops.

layout_operationA

Layout helpers: align | distribute | center | stack | applyMargins. Thin wrapper — prefer execute_batch when combining with other ops. Requires scan_document; role targets need analyze_page.

layout_assistantA

Diagnose or fix page layout (overlapping/tight text, items outside margins). Modes: diagnose | preview | fix. Prefer after scan_document (+ analyze_page for title roles). Units are points. fix applies via execute_batch.

list_stylesA

List paragraph / character / object styles from the Document Model cache (or refresh from InDesign). Prefer after scan_document; use apply_style / execute_batch applyStyle to apply.

apply_styleA

Apply a paragraph, character, or object style to target item(s). Prefer execute_batch when combining with other ops.

create_styleB

Create a paragraph/character/object style (from selection item, basedOn, and/or font size spec).

update_styleB

Update an existing style definition (spec, basedOn, rename, or copy from an item).

list_assetsA

List placed links/assets (path, status, page) from cache or refresh from InDesign.

check_missing_linksB

Report missing / inaccessible / out-of-date links in the active document.

relink_assetB

Relink a placed asset to a new file path on disk.

replace_assetB

Replace a placed asset with another file (same as relink_asset).

embed_assetB

Embed a linked asset into the document (unlink from disk).

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/anananaTERRA/mcp-indesign-agent'

If you have feedback or need assistance with the MCP directory API, please join our Discord server