Skip to main content
Glama

Application GUI catalog

app_catalog
Read-onlyIdempotent

Use this when the user needs to discover curated workflows and, with include_detected=true, new OS software records. Linux prefers visible XDG GUI launchers; macOS .app copies have separate IDs and require PID executable provenance; Windows uses local Start Menu shortcuts with exact PID executable attestation; registry-only rows cannot authorize GUI access. Detection is not proof of an active GUI, permissions or a trusted connector. Use local- ids for inspect/find-visible-controls or explicit checked focus_control and one bounded set_control_text with old-value CAS; other effects are forbidden.

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": {
      "device": "<device>"
    },
    "name": "app_catalog"
  }
}

Input Schema

NameRequiredDescriptionDefault
appNoExact app id or alias, e.g. blender, Outlook, VS Code; system for OS panels.
deviceYesReMCP device id returned by list_devices. Required for every device operation.
filterNoOptional substring matching application names, categories or direct destinations.
refreshNoForce a fresh native presence scan when check_installed=true; otherwise use the short-lived cache.
categoryNoCategory: system, office, browsers, development, media, communication, graphics, security, utilities or web.
include_guidesNoInclude detailed task-specific safe UI guidance; requires app, category or filter to avoid huge results.
check_installedNoCheck OS-specific presence hints for registered apps (not proof of absence). Optional; adds bounded native discovery latency.
include_detectedNoAlso discover unprofiled applications/packages from the current OS. Linux uses visible XDG launchers, Windows uses local Start Menu .lnk entries with executable provenance, and macOS distinguishes app bundles; read-only inventory with at most 60 entries; future installs appear after cache refresh.

Output Schema

NameRequiredDescriptionDefault
dataNoArray/scalar payload wrapper used when the natural result is not an object.
textYesConcise human-readable result of the tool call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description still adds substantive behavior beyond them: detection is explicitly not proof of an active GUI, permissions or a trusted connector, and registry-only rows 'cannot authorize GUI access' — real operational caveats that prevent an agent from over-trusting detected rows.

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

Conciseness3/5

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

The use-trigger is correctly front-loaded, but the middle section is a run-on of semicolon-chained platform facts that largely duplicate the include_detected schema description, and the closing sentence describes constraints on other tools rather than this one. Nothing is unintelligible, but the density costs readability.

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?

An output schema exists, so return-value explanation is unnecessary, and with 100% parameter coverage the description's remaining job is usage and caveats — both delivered. The main gap is that the relationship to app_execute/launch_app is only implied via 'other effects are forbidden' rather than stated, but nothing needed to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all eight parameters are already documented, including the platform-specific semantics of include_detected. The description repeats that platform detail (XDG launchers, macOS bundle IDs, Windows Start Menu shortcuts) and introduces the idea of 'local-' ids for downstream tools, but adds little parameter meaning the schema does not already supply. Baseline 3 applies.

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?

The opening sentence names a discovery trigger and the resource set ('curated workflows' plus, with include_detected=true, 'new OS software records'), which is enough to separate this read-only catalog from siblings like launch_app, app_execute or app_task. The phrase 'curated workflows' is slightly oblique versus the title 'Application GUI catalog', but the scope is recoverable from the first sentence.

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?

Explicit when-to-use is given ('Use this when the user needs to discover...') plus a conditional variant for include_detected=true, and the closing sentence constrains downstream behavior: use local- ids for inspect/find-visible-controls, or an explicit checked focus_control plus one bounded set_control_text with old-value CAS, with 'other effects are forbidden.' No named sibling alternative is offered for the non-catalog path, which keeps this below 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources