Skip to main content
Glama

construct_object

Build any 3D object from a natural language description by generating and executing Blender Python scripts. Supports adjustable complexity and style presets.

Instructions

PORTMANTEAU PATTERN RATIONALE: Consolidates natural language 3D construction into single agentic interface. Prevents tool explosion while enabling infinite 3D creativity through LLM-generated Blender scripts. Follows FastMCP 2.14.3 best practices.

Universal 3D object construction using natural language and LLM-generated Blender scripts.

This revolutionary tool enables creation of any 3D object through natural language descriptions by leveraging FastMCP 2.14.3 sampling to request SOTA LLM generation of Blender Python code.

Agentic Workflow:

  1. Analysis: Parse natural language description and scene context

  2. Sampling Request: Ask MCP client (SOTA LLM) to generate Blender Python script

  3. Code Generation: LLM creates production-ready Blender automation code

  4. Validation: Security and syntax validation of generated code

  5. Execution: Safe execution in Blender with error handling

  6. Iteration: Request refinements if needed (up to max_iterations)

Supported Complexity Levels:

  • simple: Basic primitives, basic transforms, simple materials

  • standard: Complex meshes, modifiers, materials, basic animation

  • complex: Advanced geometry, rigging, physics, complex materials/textures

Style Presets:

  • realistic: Physically accurate materials, lighting, proportions

  • stylized: Artistic interpretation, exaggerated features, cartoon-like

  • lowpoly: Minimal geometry, optimized for performance

  • scifi: Futuristic design, metallic materials, glowing effects

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ctxYesFastMCP context for sampling and conversational responses
descriptionNoNatural language description of object to create Examples: "a robot like Robbie from Forbidden Planet", "a medieval castle", "a sleek sports car"a simple cube
nameNoName for the created object in Blender scene. Default: "ConstructedObject"ConstructedObject
complexityNoComplexity level for script generation. One of: "simple", "standard", "complex". Default: "standard". Affects detail level and operation complexity.standard
style_presetNoOptional style guidance. One of: "realistic", "stylized", "lowpoly", "scifi". Default: None (let LLM decide based on description).
reference_objectsNoExisting Blender objects to use as reference for style/consistency. Default: None. LLM will analyze these objects for consistent styling.
allow_modificationsNoWhether LLM can modify existing scene objects. Default: True. Set to False for conservative construction that only adds new objects.
max_iterationsNoMaximum refinement iterations if initial script fails. Default: 3. Higher values allow more complex objects but increase processing time.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior3/5

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

No annotations provided, so description is the sole source. It details a 6-step agentic workflow, mentions validation and safe execution, and notes iteration. However, it does not address prerequisites, destructive potential (parameter allow_modifications exists but not emphasized in behavior), or error states beyond iteration.

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

Conciseness2/5

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

Description is overly verbose, opening with a non-user-facing 'PORTMANTEAU PATTERN RATIONALE' that should be removed. While structured with sections, many sentences are self-promotional and could be trimmed significantly.

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

Completeness4/5

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

Given the tool's complexity (8 params, no annotations), the description covers purpose, workflow, complexity levels, and style presets. The existence of an output schema reduces need for return details, though some information on handling failures and output format is missing.

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?

Schema coverage is 100%, so baseline is 3. The description adds context about how parameters like 'description' are used in sampling, but largely repeats schema defaults. No contradiction but limited added value.

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 clearly states it constructs 3D objects from natural language via LLM scripts. It distinguishes itself from many specialized Blender tools by being a universal interface, though it does not explicitly compare to siblings.

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

Usage Guidelines3/5

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

Implied usage for high-level creation from description, but lacks explicit guidance on when to use this vs. other Blender tools (e.g., blender_mesh, blender_ai_generate). Complexity levels and style presets offer some context but no exclusions.

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/sandraschi/blender-mcp'

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