Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

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": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
ue5_check_healthA

Check bridge/editor health: engine version, project name, loaded bridge API list. Call this first to confirm the editor is reachable before any write operation. Returns {engine_version, project, bridge_apis[]}. | 健康检查:引擎版本、项目名、bridge API 清单;任何写操作前先调用。

ue5_run_diagnosticsA

Full bridge diagnostics: complete C++ API method matrix and any missing critical APIs. Use when a tool fails with an API-missing error, or after upgrading/replacing the bridge DLL. | Bridge 诊断:全部 C++ API 方法矩阵 + 关键 API 缺失项。

ue5_list_assetsA

List asset paths under a content folder (default /Game/). Use to discover what exists before reading or editing. recursive=true walks subfolders. | 列出 /Game 资产路径(recursive 控制是否递归)。

ue5_read_blueprintA

Read a Blueprint asset: level L1 = class info + variables + CDO, L2 = node graph + connections, full = both. Read-only and safe to call any time. Returns structured JSON (Markdown/Mermaid reports available via the CLI reader). | 读取蓝图(L1 类信息+变量+CDO / L2 节点+连线 / full)。

ue5_read_nodesA

Read Blueprint nodes: titles, positions, GUIDs and pin defaults. Omit graph_name to search all graphs. Use before connecting pins so you have the GUIDs. | 读取蓝图节点(不传 graph_name = 全图搜索)。

ue5_read_connectionsA

Read the Blueprint's connection topology (which pin connects to which node/pin). Use to verify wiring before and after edits. | 读取蓝图连线拓扑。

ue5_build_blueprintA

Create a Blueprint from scratch in one atomic call: asset + variables + components + interfaces + events + function nodes + connections + optional compile. If any step fails, assets created by this call are rolled back. spec fields: blueprint_name (or name), package_path, parent_class, variables[{name,type,default_value,category}], components[{name,component_class,properties}], interfaces[str], events[{event_name|name,pos}], functions[{function_name|name, target_class, function_path, defaults:{pin:val}, pos}], connections[{src_node,src_pin,dst_node,dst_pin}], compile_after. Node references accept 32-hex GUIDs (recommended) or titles. | 创建蓝图(原子化:失败回滚已建资产)。

ue5_build_batchA

Create multiple Blueprints in one atomic batch: if any blueprint fails, all assets created by this batch are rolled back. Prefer ue5_build_blueprint unless multi-asset atomicity is actually needed. | 批量创建蓝图(原子化:任一失败回滚本批已建资产)。

ue5_compile_blueprintA

Compile a Blueprint, read back the compile status and scan the log for error patterns. The real compile result is reported: a failed compile returns failure with log evidence, never a fake success. | 编译蓝图 + 回读编译状态 + 日志错误模式扫描。

ue5_connect_pinsA

Connect pins with triple topology verification (existence, type compatibility, read-back). Node references accept titles or 32-hex GUIDs; ambiguous titles are rejected (fail-loud) — use GUIDs when titles repeat. | 引脚连线(三重拓扑验证;标题歧义 fail-loud 拒绝)。

ue5_disconnect_pinB

Disconnect every connection attached to one pin of a node, verified against the live topology. | 断开节点某引脚的全部连线(按实时拓扑验证)。

ue5_delete_nodeA

Delete a Blueprint node. dry_run=true only checks references without deleting — use it first for nodes that may be referenced elsewhere. | 删除节点(dry_run 仅检查引用,不删除)。

ue5_save_assetA

Save an asset to disk; only_if_is_dirty=true skips clean packages. Saves are scoped to the asset's own package — this tool never triggers a whole-project save. | 保存资产落盘(only_if_is_dirty=true 仅脏包写盘;作用域=该资产包,绝不全工程保存)。

ue5_delete_assetA

Delete an asset with reference checks and read-back verification. Save scope = referencing packages only. | 级联删除资产(删后回读验证;保存作用域=引用者包)。

ue5_start_pieA

Start PIE (play/simulate) asynchronously. Poll with ue5_read_pie_state until is_playing=true. Use to verify that logic actually RUNS, not just that it compiles. | 启动 PIE/Simulate(异步;用 ue5_read_pie_state 轮询确认)。

ue5_stop_pieB

Stop the running PIE/Simulate session. | 结束 PIE/Simulate 会话。

ue5_read_pie_stateA

Read PIE state: is_playing, world name, paused, game time. Poll this after ue5_start_pie before reading runtime actors/properties. | PIE 状态:is_playing / 世界名 / 暂停 / 游戏时间。

ue5_list_pie_actorsA

Enumerate live Actors in the PIE world (runtime objects; their paths contain UEDPIE_0_). Filter by actor_class and/or name_filter substring; limit caps the result count. | 枚举 PIE 世界 Actor(运行时对象)。

ue5_read_pie_propertyA

Read a runtime Actor property in PIE; omit property_name to list candidate property names first. Use this to prove game logic ran (e.g. health changed after a pickup). | 读 PIE 中 Actor 属性(property_name 空 = 列候选属性名)。

ue5_set_pie_transformA

Teleport a PIE Actor at runtime (location and/or rotation, at least one), with read-back verification of the new transform. | 运行时传送 PIE Actor(location/rotation 至少一个;带回读验证)。

ue5_read_logsA

Read the UE log: cursor=0 returns the tail (last lines); cursor>0 returns only new lines after that cursor (incremental polling). Filter by category/pattern. Use for self-service cross-checks of any operation. | 读 UE 日志(cursor=0 取尾部;cursor>0 增量取新增;category/pattern 过滤)。

ue5_run_batchA

Execute a whitelisted-command batch in one request (multi-step task in a single round trip); stops on the first failing step by default. For a single operation prefer the dedicated tool — this is for sequences. | 白名单命令批量执行(单次请求多步;任一步失败默认中止)。

ue5_execute_commandA

Escape hatch: run any whitelisted bridge command by name — the full 72-command surface, including capabilities without a dedicated tool (materials, UMG widgets, and other advanced operations). Prefer the dedicated tool whenever one exists for the operation; this generic entry point is the last resort and its arguments are less validated. command ∈ add_actor_bound_event_node, add_async_action_node, add_cast_node, add_class_cast_node, add_comment_node, add_component, add_component_bound_event_node, add_composite_node, add_create_delegate_node, add_custom_event_node, add_enum_literal_node, add_event_dispatcher, add_function_node, add_function_pin, add_implemented_interface, add_input_action_event_node, add_input_axis_event_node, add_input_key_event_node, add_local_variable, add_macro_node, add_math_expression_node, add_pin_to_node, add_struct_node, add_switch_node, add_timeline_node, add_variable, add_variable_node, build_blueprint, compile_blueprint, connect_pins, create_node_by_class, delete_asset, editor_batch, find_actors, get_actor_properties, get_node_by_guid, get_pin_default_value, health, list_assets, logs_read, material_add_expression, material_compile, material_connect_expressions, material_connect_property, material_create, material_instance_create, material_instance_set_parameter, material_read, material_set_expression_property, pie_start, pie_state, pie_stop, read_blueprint, read_cdo, read_connections, read_nodes, read_variables, remove_component, remove_pin_from_node, save_asset, set_actor_transform, set_class_default, set_node_position, set_node_property, set_pin_default_value, spawn_actor, try_node_add_input_pin, unpin_console_refs, widget_add_child, widget_create, widget_read_tree, widget_set_property;params 为该命令入参对象。未登记命令 fail-loud 拒绝。| 白名单命令透传(专用工具未覆盖时使用)。

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.9/5.0

Scored across 23 tools

Disambiguation5/5

Every tool has a distinct purpose: lifecycle (build, compile, connect, delete), read (nodes, connections, topology), PIE runtime operations, and diagnostics/health. Overlaps like ue5_read_blueprint vs. ue5_read_nodes are clearly scoped (whole asset vs. specific graph), and ue5_run_batch vs. ue5_execute_command are clearly differentiated (whitelisted sequences vs. escape hatch).

Naming Consistency4/5

Naming is highly consistent with a verb_noun pattern (e.g., ue5_list_assets, ue5_read_blueprint, ue5_delete_asset), and all tools share the ue5_ prefix. Minor deviation: ue5_run_batch and ue5_execute_command are more generic verbs ('run' vs. 'execute') but still readable and not chaotic.

Tool Count3/5

At 23 tools, the surface is on the heavy side but still scoped to the domain (Blueprints, assets, PIE, diagnostics, audio/video). A few tools like ue5_build_batch or ue5_disconnect_pin are edge-case, and ue5_execute_command duplicates many others as an escape hatch, making the count feel slightly inflated. Still, each tool has a defensible role.

Completeness5/5

The toolset covers the full Blueprint lifecycle: create (build, batch), read (list, read_blueprint, read_nodes, read_connections), modify (connect, disconnect, delete_node, save), and verify (compile, PIE start/stop/read, logs, diagnostics). It also covers delete_asset and runtime property access. Missing operations are minimal and covered by the escape hatch (ue5_execute_command).

Maintenance

ActivityMaintained
ResponsivenessNo issues