Skip to main content
Glama
Flux-Point-Studios

Unreal Engine MCP Server

manage_ai

Create AI Controllers, configure Behavior Trees, Blackboards, EQS queries, and perception systems in Unreal Engine.

Instructions

Create AI Controllers, configure Behavior Trees, Blackboards, EQS queries, and perception systems.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoName identifier.
pathNoDirectory path for asset creation.
actionYesAI action to perform
nodeIdNoID of the node.
teamIdNoTeam ID for perception affiliation (0=Neutral, 1=Player, 2=Enemy, etc.).
keyNameNoName of the key.
keyTypeNoBlackboard key data type.
toStateNoTarget state name.
taskTypeNoTask node type.
testTypeNoEQS test type.
enumClassNoEnum class for Enum keys.
fromStateNoSource state name.
queryPathNoPath to EQS query asset.
slotIndexNoIndex of slot to configure.
stateNameNoName of the state.
testIndexNoIndex of test to configure.
configPathNoPath to config asset.
massTraitsNoList of Mass traits to add.
slotOffsetNoLocal offset for slot.
contextTypeNoEQS context type.
parentClassNoParent class for AI controller (default: AAIController).
serviceTypeNoService node type.
sightConfigNoAI sight sense configuration.
slotEnabledNoWhether slot is enabled.
damageConfigNoAI damage sense configuration.
parentNodeIdNoID of the node.
slotRotationNoLocal rotation for slot.
slotUserTagsNoRequired user tags for slot.
testSettingsNoTest scoring and filter settings.
blueprintPathNoBlueprint asset path.
compositeTypeNoComposite node type.
decoratorTypeNoDecorator node type.
dominantSenseNoDominant sense for perception prioritization.
generatorTypeNoEQS generator type.
hearingConfigNoAI hearing sense configuration.
stateTreePathNoPath to State Tree asset.
blackboardPathNoPath to blackboard asset.
controllerPathNoPath to controller blueprint.
definitionPathNoPath to definition asset.
massProcessorsNoList of Mass processors to configure.
nodePropertiesNoProperties to set on the node.
stateTaskClassNoTask class for state.
baseObjectClassNoBase class for Object/Class keys.
customTaskClassNoCustom task class path for Custom task type.
spawnerSettingsNoMass spawner configuration.
behaviorTreePathNoPath to behavior tree asset.
isInstanceSyncedNoSync key across instances.
slotActivityTagsNoActivity tags for the slot.
generatorSettingsNoGenerator-specific settings.
customServiceClassNoCustom service class path.
autoRunBehaviorTreeNoStart behavior tree automatically on possess.
stateEvaluatorClassNoEvaluator class for state.
transitionConditionNoCondition expression for transition.
customDecoratorClassNoCustom decorator class path.
slotBehaviorDefinitionNoGameplay behavior definition for slot.
Behavior2/5

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

Annotations already indicate this is not read-only and not flagged as destructive. However, the description adds no additional behavioral context beyond listing operations. It fails to disclose potential asset overwrites, required project setup, or effects of repeated calls, which is significant given the sparse annotations.

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 sentence with no filler, front-loading the primary verb and resources. It is efficiently structured and every word earns its place.

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?

A 55-parameter tool with 44 actions and no output schema needs more high-level orientation. The description doesn't explain how actions are organized, what typical workflows look like, or how the action parameter drives behavior. It is an adequate summary but not complete enough for such a complex 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?

All 55 parameters have schema descriptions (100% coverage), so the schema carries the semantic burden. The tool description adds only high-level resource categories and does not explain parameter relationships or the central role of the 'action' parameter. Minimal added value beyond what the schema already provides.

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?

The description uses specific verbs 'Create' and 'configure' and explicitly names five distinct AI resource types: AI Controllers, Behavior Trees, Blackboards, EQS queries, and perception systems. This clearly distinguishes it from the sibling tool manage_behavior_tree by covering a broader AI management scope.

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?

The description provides no explicit guidance on when to use this tool versus dedicated sibling tools like manage_behavior_tree, nor any exclusions or prerequisites. It simply lists capabilities without contextual steering about which action to choose or when an alternative would be more appropriate.

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/Flux-Point-Studios/unreal-mcp'

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