Skip to main content
Glama

scene

Destructive

Create, read, edit, and save Godot node hierarchies. Add, remove, inspect, and instance nodes and resources.

Instructions

场景操作。读取/创建: read_scene, create_scene, quick_scene。节点: add_node, batch_add_nodes, edit_node, remove_node。保存/资源: save_scene, load_sprite。查询: query_scene_tree, inspect_node。实例: instance_scene, set_instance_property, detach_instance。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNocreate_3d_node: 节点名称
saveNocommit: 是否保存到文件(默认 true)
typeNocreate_3d_node: 节点类型(仅限白名单)
nodesNobatch_add_nodes: 节点定义数组
valueNoset_instance_property: 属性值(string/number/bool/null/array)
actionYes操作类型
parentNocreate_3d_node: 父节点路径(默认 root)
new_pathNosave_scene: 新保存路径(可选)/ merge_scene: theirs 场景路径(必需)
propertyNoset_instance_property: 属性名
max_depthNoquery_scene_tree/inspect_node: 最大遍历深度
node_nameNoadd_node: 节点名称
node_pathNoinspect_node/edit_node/remove_node/load_sprite/detach_instance/set_instance_property: 节点路径
node_typeNoadd_node: 节点类型(如 Sprite2D, Camera2D)
godot_pathNo覆盖 Godot 二进制路径(可选,优先于项目配置和环境变量)
operationsNocommit: 批量操作列表(tile_set/tile_fill/tile_erase/tile_clear/tileset_assign/node_property/node_add)
propertiesNoadd_node/edit_node/instance_scene: 属性对象
scene_pathNo场景路径(read_scene 用绝对路径,其余用相对项目路径)
script_pathNoquick_scene: 脚本路径(可选)
project_pathNoGodot 项目目录路径
summary_onlyNoread_scene: 返回摘要而非完整 JSON
texture_pathNoload_sprite: 纹理路径(如 res://assets/player.png)
instance_pathNoinstance_scene: 要实例化的场景文件(res://scenes/player.tscn)
stop_on_errorNocommit: 遇错是否停止(默认 true)
load_autoloadsNo是否加载 Autoload 上下文(默认 true)
root_node_nameNoquick_scene: 根节点名称(默认从文件名推导 PascalCase)
root_node_typeNocreate_scene/quick_scene: 根节点类型(默认 Node2D)
script_contentNoquick_scene: 脚本内容(脚本不存在时自动创建)
include_signalsNoinspect_node: 包含信号连接(默认 true)
parent_node_pathNoadd_node/instance_scene: 父节点路径(默认 root)
include_propertiesNoinspect_node: 包含属性值(默认 true)
Behavior2/5

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

Annotations already indicate destructiveHint=true, but the description adds no further context about what gets destroyed or modified, such as file writes, save defaults, or irreversibility of remove/save actions. The listed action names imply mutating operations, but the description does not explicitly disclose side effects or safety considerations beyond what annotations already state.

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?

The description is a single, front-loaded sentence that uses clear category separators to organize the many sub-actions. It contains no filler or redundancy, making it appropriately sized for a dispatcher-style overview, though it sacrifices depth for brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (30 parameters, no output schema, and a large action enum), the description is insufficiently complete. It does not explain the required `action` parameter, how actions are selected, what return values look like, or how the operations chain together, leaving significant gaps for an agent trying to use the tool correctly.

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?

Parameter semantics are fully covered by the input schema (100% coverage), so the baseline is 3. The description contributes no additional parameter-level meaning; it only lists action names and does not explain fields like `scene_path`, `node_path`, or `operations`, which remain reliant on the schema's own descriptions.

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 description opens with '场景操作' (scene operations) and groups the many action enum values into meaningful categories (read/create, node, save/resource, query, instance), which clarifies the tool's scope and distinguishes it from sibling tools like editor or ui. However, it lacks a single specific verb+resource statement, relying on the action list to convey purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance is given about when to use this tool versus alternatives, nor are there exclusions or preferred action choices. The categorized list implies some usage contexts (e.g., read_scene for reading, add_node for adding), but it does not state when to choose `scene` over sibling tools like `editor` or `tilemap`.

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

Install Server

Other Tools

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/wgt19861219/godot-mcp-enhanced'

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