Unreal-MCP-Ghost

by CrispyW0nton

Overview Schema Source Related Servers Discussions Admin

Python

Local

bp_inspect_node

Retrieve a Blueprint node's full pin and connection details to reveal exact pin names needed for connecting pins.

Instructions

Get full pin and connection details for a single Blueprint node.

Use this after bp_add_node to see the exact pin names before calling bp_connect_pins. Pin names returned here are the exact strings you must pass to bp_connect_pins.

Returns a StructuredResult with: outputs.node_id — the node's GUID outputs.node_name — short object name outputs.node_type — type string outputs.title — human-readable title outputs.pos_x, pos_y — canvas position outputs.pins — list of all pins: pin_name — exact name to use in bp_connect_pins direction — 'input' | 'output' pin_type — type string (exec, bool, float, object, etc.) default_value — current default value (empty if not set) linked_to — list of {node_id, pin_name} for connected pins

Args: blueprint_name: Blueprint asset name node_id: GUID or short object name from bp_add_node graph_name: Graph containing the node. Default 'EventGraph' include_hidden_pins: Include internal pins. Default False.

Returns: JSON string with StructuredResult.

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

Input Schema

TableJSON Schema

Name	Required	Default
`node_id`	Yes
`graph_name`	No	EventGraph
`blueprint_name`	Yes
`include_hidden_pins`	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

A4.5/5.0

Behavior4/5

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

No annotations are present, so the description carries the burden; it compensates by fully enumerating the StructuredResult fields and pin subfields, including pin direction, type, default value, and linked connections. It does not explicitly declare that the operation is read-only, but the 'Get' verb and output-only framing make side effects unlikely.

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 front-loaded and well-organized with Args, Returns, KB, and Example sections. It is fairly long, but each section adds value; the only minor redundancy is the 'Returns: JSON string with StructuredResult' line repeating the earlier structured result list.

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?

The description is complete for invocation: it explains the exact workflow, all parameters and defaults, the output structure, a KB reference, and a concrete example. An agent can correctly select and call 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?

Despite 0% schema coverage, the Args section gives every parameter meaningful guidance beyond the schema: blueprint_name includes an example asset path, node_id explains accepted GUID or short object name from bp_add_node, graph_name provides default context, and include_hidden_pins clarifies internal pins. This fully compensates for the bare schema.

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 full pin and connection details for a single Blueprint node.' It clearly distinguishes this from sibling node-listing and graph-summary tools by emphasizing the pin-level detail and connection data.

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 explicitly places the tool in a workflow: after bp_add_node and before bp_connect_pins, and states that returned pin names are the exact strings to pass. It does not name alternatives or state when-not-to-use, so it falls just short of the top score.

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

Deploy Server