Skip to main content
Glama
Sign In

Dockyard — MCP server for the app catalog

by ovh.kim1.dockyard
OverviewDiscussionsAdmin

Search apps

list_apps
Read-onlyIdempotent

Searches the Dockyard catalog. Returns short cards (slug, title, category, kind, image). The full description and the deployment plan come from get_app and prepare_deploy.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_apps"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoKind of entry.
limitNoDefaults to 20 when omitted. Values outside 1–50 are rejected.
queryNoWords from the name, description, image, or category. Every word must match.
offsetNoHow many cards to skip from the start of the list. Defaults to 0. Negative values are rejected.
categoryNoExact category, case-insensitive.

Output Schema

NameRequiredDescriptionDefault
appsYes
limitYes
totalYes
offsetYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / category / description
      Previous value: -"Dokładna kategoria, bez rozróżniania wielkości liter."New value: +"Exact category, case-insensitive."
    • changedInput schema / properties / kind / description
      Previous value: -"Rodzaj wpisu."New value: +"Kind of entry."
    • changedInput schema / properties / limit / description
      Previous value: -"Domyślnie 20, maksimum 50."New value: +"Defaults to 20 when omitted. Values outside 1–50 are rejected."
    • changedInput schema / properties / offset / description
      Previous value: -"Ile kart pominąć od początku listy. Domyślnie 0."New value: +"How many cards to skip from the start of the list. Defaults to 0. Negative values are rejected."
    • changedInput schema / properties / query / description
      Previous value: -"Słowa z nazwy, opisu, obrazu albo kategorii. Wszystkie muszą pasować."New value: +"Words from the name, description, image, or category. Every word must match."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "apps": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "category": {
+            "type": "string"
+          },
+          "description": {
+            "type": "string"
+          },
+          "image": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "kind": {
+            "type": "string"
+          },
+          "slug": {
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "slug",
+          "title",
+          "category",
+          "kind",
+          "image",
+          "description"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "limit": {
+      "maximum": 50,
+      "minimum": 1,
+      "type": "integer"
+    },
+    "offset": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "total": {
+      "minimum": 0,
+      "type": "integer"
+    }
+  },
+  "required": [
+    "total",
+    "offset",
+    "limit",
+    "apps"
+  ],
+  "type": "object"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / offset / description
      Added value: +"Ile kart pominąć od początku listy. Domyślnie 0."
  3. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, so the safety profile is covered. The description adds real value by disclosing the result shape (short cards with slug, title, category, kind, image) and warning that the card is not the full record. It says nothing about ordering or result-cap behavior, but the schema covers limit bounds.

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?

Two sentences, zero filler, scope stated first and the sibling hand-off second. Every clause carries information the agent needs.

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?

With an output schema present, the description need not re-document return values, yet it still summarizes the card fields so the agent knows whether to call a sibling next. Rich annotations plus full schema coverage leave no meaningful gap for a five-parameter search tool.

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%, including defaults, bounds, enum values, and the AND-matching rule for query words, so the schema carries the parameter burden. The description adds no filtering semantics of its own beyond implying a search. Baseline 3 applies.

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?

"Searches the Dockyard catalog" gives a specific verb plus resource, and the second sentence explicitly delineates the boundary with get_app and prepare_deploy. An agent knows exactly what this tool returns (short cards) versus what the siblings return (full description, deployment plan).

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 frames this as the discovery/listing step and routes the agent to get_app and prepare_deploy for detail, which is the key routing decision. It does not spell out exclusion cases such as when to skip search entirely, but the when-to-use context is unambiguous.

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

All Dockyard — MCP server for the app catalog toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources