Unreal-MCP-Ghost

Overview Schema Source Related Servers Discussions Admin

bp_get_graph_summary

Get a compact, AI-readable summary of a Blueprint graph, including variables, functions, events, and paginated node lists. Use it to inspect graph structure or fetch metadata-only details.

Instructions

Get a compact, AI-readable summary of a Blueprint graph.

V5 enhancements over V4.1:

Always returns top-level variables[], function_graphs[], event_graphs[]
Pagination when include_nodes=True (page / page_size)
include_nodes=False returns only metadata (variables, graphs) — very compact

Output format (outputs dict): blueprint: str — Blueprint asset name graph: str — Graph name queried node_count: int — Total nodes in this graph page: int — Current page (0-based) total_pages: int — Total pages variables: list — [{name, type}] — all Blueprint member variables function_graphs: list — [{name, type:'function'}] event_graphs: list — [{name, type:'event'}] nodes: list — Node entries (empty when include_nodes=False) summary_text: str — Compact one-liner per node

Args: blueprint_name: Blueprint asset name (e.g. 'BP_HealthSystem') graph_name: Graph to inspect. Default 'EventGraph'. include_pin_defaults: Include pin default values. Default True. include_positions: Include node canvas positions. Default True. include_nodes: Include node list. Set False for metadata-only. Default True. page: 0-based page index when include_nodes=True. Default 0. page_size: Nodes per page. Default 50.

Returns: JSON string with StructuredResult.

KB: see knowledge_base/01_BLUEPRINT_FUNDAMENTALS.md#overview Example: bp_get_graph_summary(blueprint_name="/Game/MCP_Test/BP_Example")

Input Schema

TableJSON Schema

Name	Required	Default
`page`	No
`page_size`	No
`graph_name`	No	EventGraph
`include_nodes`	No
`blueprint_name`	Yes
`include_positions`	No
`include_pin_defaults`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Sep 20, 2026

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden. It explicitly discloses always-returned arrays, pagination behavior, the effect of include_nodes, the complete output dict, and the JSON string return format. This goes well beyond what the schema alone conveys.

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

Conciseness4/5

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

The description is well-organized with clear sections for output format, args, returns, KB reference, and an example. It is dense but not bloated; the only minor trimming opportunity is the 'V5 enhancements over V4.1' framing, which adds historical context but is not essential for an agent.

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?

For a tool with 7 parameters and no schema-level descriptions, this definition is exceptionally complete: it documents all parameters, their defaults, the output contract field-by-field, and an example call. An agent can confidently select and invoke this tool without needing additional context.

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

Parameters5/5

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

The schema has 0% description coverage, but the tool description compensates fully by explaining every parameter in plain language, including defaults and special notes like 'Set False for metadata-only' and '0-based page index.' Each parameter's purpose is clear enough to invoke the tool correctly.

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 opens with a specific verb and resource: 'Get a compact, AI-readable summary of a Blueprint graph.' It clearly distinguishes this from sibling inspection tools like bp_get_graph_detail by emphasizing the compact, graph-level summary nature and listing the exact output sections.

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?

The description provides clear usage context, such as when to set include_nodes=False for metadata-only results and how pagination works. However, it does not explicitly contrast this tool with alternatives like bp_get_graph_detail or get_blueprint_graphs, so the when-to-use guidance is implicit rather than comparative.

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

Deploy Server