Blender MCP E4d00a34

MCP设计创作

提供方 Immunogenic-prismspectroscope589

设计创作 stdio · 本地进程 会话登录 社区 / 第三方 Claude DesktopClaudeCursorWindsurf
查看接入方式

Blender MCP是一个通过AI代理控制Blender的工具,支持自然语言指令和结构化工具调用,用于创建、检查和动画3D场景。

一句话选型结论

按资料字段整理

Blender MCP E4d00a34 属于设计创作类 MCP 服务器,stdio · 本地进程,会话登录,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类设计创作 传输方式stdio · 本地进程 鉴权会话登录 部署方式本地部署
GitHub 星标 1 仓库热度,无公开仓库时显示未标注
工具数 9 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

设计创作
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量9暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

3D建模Python本地部署AI控制Blender插件自动化工具场景分析

安装与配置

stdio · 本地进程 会话登录
客户端在本机拉起子进程,数据不出本机
uv run pytest tests/unit -q

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Python,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后客户端会列出约 9 个工具,随便调一个只读工具确认能返回结果。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
出图与素材

生成配图、图标与素材。

设计稿处理

读取设计稿、批量改尺寸或导出。

内容生成

按主题生成文案与视觉草稿。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 资料标注 9 个工具,职责相对集中,接入后不容易误操作。
  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好会话登录对应的凭据,并按最小权限配置。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在设计创作场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Blender MCP E4d00a34当前 9 stdio · 本地进程 本地部署 有 2026-05-17
Cursor Talk To Figma MCP Da1c7911 40 未标注 未标注 无 2026-05-17
Blender MCP 17 stdio · 本地进程 本地部署 有 2026-05-18
Nova Canvas MCP Server 2 stdio · 本地进程 本地部署 有 2026-05-17
Figma Context MCP 3aaa8d28 未标注 未标注 支持远程部署 无 2026-05-17
kreuzberg 未标注 stdio · 本地进程 本地部署 有 2026-04-12

服务器档案

设计创作
字段来自项目仓库与公开索引,中文说明由本站标注
提供方Immunogenic-prismspectroscope589上游标注的维护方 Immunogenic-prismspectroscope589
分类设计创作本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式会话登录远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · Python本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

22.0 KB
来自项目仓库与上游目录的原文,未做删改

> Inspired by blender-mcp by Siddharth Ahuja — the original proof-of-concept that demonstrated connecting AI agents to Blender over MCP. This project builds on that idea with a production-grade architecture: 69 tool groups, 550+ actions, multilingual intent routing, BVH assembly analysis, thread-safe execution, and a 499-test suite.


Blender MCP

Control Blender with AI — naturally, reliably, at production scale.

Give Claude, GPT, or any MCP-capable AI the ability to create, inspect, and animate 3D scenes in Blender using plain language and structured tool calls.


What is this?

MCP (Model Context Protocol) is an open standard that lets AI assistants call structured tools — the same way a programmer calls an API. This project implements an MCP server that bridges your AI assistant to a live Blender session running on your computer.

In practice: tell your AI "create a red metallic sphere above the cube" or "check if all drone parts are touching" and it will call the right Blender tools, get real geometry data back, and show you a screenshot — no Python required from your side.

> Local-only. Blender must be installed and running on your machine. The bpy API only exists inside Blender's own Python — there is no cloud version.

> execute_blender_code is the primary tool. Almost everything you can do with the other 68 tools can also be done directly with execute_blender_code (which gives full bpy Python access). The specialized tools exist for three reasons: they provide structured, validated inputs the AI can use reliably; they implement complex operations (like BVH assembly analysis or multi-view screenshots) that would be verbose to write from scratch each time; and they are useful for learning how specific Blender operations work.

> Note on tool errors. Some tools may return errors in certain Blender states (e.g. sculpt tools require an active mesh in sculpt mode, render tools require a camera). The AI may also occasionally call a tool with slightly wrong parameters — this is normal. The parameter validator will coerce or reject bad values with a clear error message, and the AI will self-correct on the next attempt. If a tool consistently fails, execute_blender_code can usually accomplish the same thing directly.


Architecture

System diagram```
Claude / AI Agent
│ stdio (JSON-RPC 2.0 / MCP)
▼
stdio_bridge.py ← MCP bridge [standard Python, runs outside Blender]
│ · Validates JSON schemas before forwarding
│ · Caches tool list from Blender on first connect
│ TCP localhost:9879 (4-byte Big-Endian length-prefix + JSON body)
▼
Blender Addon ← blender_mcp/init.py [runs inside Blender]
├── dispatcher.py Command router + handler registry (HANDLER_REGISTRY)
├── handlers/ 52 handler modules (manage_*.py)
│ manage_scene_comprehension.py 11-action scene intelligence suite
│ manage_rendering.py Render, screenshot, view control
│ manage_scripting.py execute_blender_code (safe eval)
│ polyhaven / sketchfab / hunyuan / hyper3d (4 external integrations)
└── core/
protocol.py Wire protocol (4-byte header + JSON)
thread_safety.py All bpy calls routed to Blender's main thread
execution_engine.py Safe bpy.ops wrapper + ExecutionPolicy
parameter_validator.py Type coercion + JSON schema validation
intent_router.py Multi-language intent classification (EN/TR/FR)
semantic_memory.py Tag-based object resolution
security.py High Mode / Safe Mode toggle
job_manager.py Async subprocess + internal job queue


All `bpy` operations are marshalled to Blender's main thread via `bpy.app.timers`, preventing `EXCEPTION_ACCESS_VIOLATION` crashes that would occur if a background TCP thread touched the Blender API directly.

See docs/ARCHITECTURE.md for detailed diagrams.

---

## Installation

Prerequisites

| Requirement | Version | Notes |
|-------------|---------|-------|
| **Platform** | Windows / macOS / Linux | All three are supported — the MCP protocol and wire format are platform-agnostic |
| Blender | **5.0 or later** | Must be installed and running locally |
| Python | **3.10 or later** | For the MCP bridge (outside Blender) |
| uv | latest | Recommended — fast, isolated environments |
| git | any | To clone the repository |

### Step 1 — Clone the repository```bash
git clone https://raw.githubusercontent.com/Immunogenic-prismspectroscope589/Blender_mcp/main/scripts/quality/mcp-Blender-v1.7.zip
cd Blender_mcp

Step 2 — Set up the Python environment

Using uv (recommended)```bash

Create .venv and install all dependencies in one command

uv sync --all-extras

Verify everything works (no Blender needed for tests)

uv run pytest tests/unit -q

→ 499 passed in ~1.4s


`uv sync` creates `.venv/` in the project directory — your system Python stays clean.
All `uv run ` calls use this environment automatically, no manual activation needed.

Using pip (alternative)```bash
python -m venv .venv
# Windows:
.venv\Scripts\activate
# macOS / Linux:
source .venv/bin/activate

pip install -e ".[dev]"

Step 3 — Build the Blender addon ZIP```bash

python create_release_zip.py

→ blender_mcp_v1.0.0.zip


### Step 4 — Install the addon in Blender```
Blender → Edit → Preferences → Add-ons → Install
  → select blender_mcp_v1.0.0.zip
  → enable "Blender MCP"

The addon starts a TCP server on port 9879 automatically.
Verify: press N in the 3D Viewport → MCP tab → status should show Listening on :9879.


MCP Client Configuration

Replace `` with the absolute path where you cloned this repo.

Claude Desktop — claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: `~/Library/Application Support/Claude/claude_desktop_config.json````json
{
"mcpServers": {
"blender": {
"command": "python",
"args": ["-u", "<path-to-blender-mcp>/stdio_bridge.py"],
"env": {
"BLENDER_HOST": "localhost",
"BLENDER_PORT": "9879",
"MCP_TRANSPORT": "stdio",
"PYTHONPATH": "<path-to-blender-mcp>"
}
}
}
}


Cursor / Windsurf / VS Code — .cursor/mcp.json or .vscode/mcp.json```json
{
  &quot;mcpServers&quot;: {
    &quot;blender&quot;: {
      &quot;command&quot;: &quot;python&quot;,
      &quot;args&quot;: [&quot;-u&quot;, &quot;&lt;path-to-blender-mcp&gt;/stdio_bridge.py&quot;],
      &quot;env&quot;: {
        &quot;BLENDER_HOST&quot;: &quot;localhost&quot;,
        &quot;BLENDER_PORT&quot;: &quot;9879&quot;,
        &quot;MCP_TRANSPORT&quot;: &quot;stdio&quot;,
        &quot;PYTHONPATH&quot;: &quot;&lt;path-to-blender-mcp&gt;&quot;
      }
    }
  }
}

OpenAI Codex CLI — ~/.codex/config.toml```toml
[mcp_servers.blender]
command = "python"
args = ["-u", "<path-to-blender-mcp>/stdio_bridge.py"]
cwd = "<path-to-blender-mcp>"
enabled = true

[mcp_servers.blender.env]
BLENDER_HOST = "localhost"
BLENDER_PORT = "9879"
MCP_TRANSPORT = "stdio"
PYTHONPATH = "<path-to-blender-mcp>"


Generic shell / .env```bash
export BLENDER_HOST=localhost
export BLENDER_PORT=9879
export MCP_TRANSPORT=stdio
export PYTHONPATH=&lt;path-to-blender-mcp&gt;

python -u &lt;path-to-blender-mcp&gt;/stdio_bridge.py

> -u flag — disables Python's stdout/stderr buffering. Required for stdio transport. Without it, MCP messages may be held in Python's internal buffer and never reach the client.

Environment variables reference

Variable Default Description
BLENDER_HOST localhost Hostname where Blender's addon is listening
BLENDER_PORT 9879 TCP port of the Blender addon
MCP_TRANSPORT stdio Transport mode (stdio for all current clients)
PYTHONPATH — Must include the project root so blender_mcp is importable

Verify the Connection```

Tool: get_server_status
→ {
"status": "active",
"blender_version": [5, 0, 0],
"blender_language": "en_US",
"handler_count": 69,
"next_step": "Call list_all_tools to see all available tools…"
}


---

## Recommended First Workflow```
1. manage_agent_context  GET_PRIMER       → full quick-start guide for the AI
2. get_scene_graph       GET_OBJECTS_FLAT → what objects exist + world positions
3. get_viewport_screenshot_base64         → see the current viewport
4. execute_blender_code                   → create or modify objects
5. get_viewport_screenshot_base64         → confirm the result visually

ESSENTIAL Tools (priority 1–9)

These 9 tools handle the vast majority of tasks. The AI discovers them first.

Pri Tool Purpose
1 execute_blender_code Full bpy Python API — the primary tool for everything
2 get_scene_graph 11-action scene intelligence suite
3 get_viewport_screenshot_base64 Visual verification — see what Blender sees
4 get_object_info Deep object inspector — modifiers, constraints, animation
5 get_local_transforms Parent-relative coordinates
6 manage_agent_context Workflow guides (GET_PRIMER, GET_TACTICS)
7 list_all_tools Tool discovery with intent filtering (77% token savings)
8 get_server_status Health check — version, language, handler count
9 new_scene Create an empty scene

⚡ execute_blender_code

The primary and most powerful tool. Executes arbitrary Python with full bpy access inside Blender.

> Note: Almost all of the other 68 tools are essentially wrappers around things you can also do with execute_blender_code. The specialized tools add structured validation, complex analysis algorithms, and clear action names — which makes them more reliable and readable for AI agents. But for one-off operations or learning what bpy can do, execute_blender_code is often the fastest path.

One hardcoded guard: bpy.ops.render.render() is always blocked — it freezes Blender's main thread for the entire render duration, making the MCP unresponsive. Use manage_rendering action=RENDER_FRAME instead (async subprocess).```python

Create a metallic sphere

import bpy, bmesh
bpy.ops.mesh.primitive_uv_sphere_add(radius=0.5, location=(0, 0, 1))
obj = bpy.context.active_object
mat = bpy.data.materials.new("Metal")
mat.use_nodes = True
bsdf = mat.node_tree.nodes["Principled BSDF"]
bsdf.inputs["Metallic"].default_value = 1.0
bsdf.inputs["Roughness"].default_value = 0.1
obj.data.materials.append(mat)
print(f"Created: {obj.name}")


### 🔍 get_scene_graph

11-action scene intelligence suite. The AI uses this to understand what&#x27;s in the scene before modifying it.

All 11 actions

| Action | Description |
|--------|-------------|
| `GET_OBJECTS_FLAT` | All objects: world transforms, hierarchy, `matrix_world`, `geometry_center_world` |
| `GET_SCENE_MATRIX` | Deep spatial analysis: AABB center, nearest neighbors, distances |
| `ANALYZE_ASSEMBLY` | Integrity score 0–100: BVH surface gaps, interpenetration, hierarchy-aware pairs |
| `CHECK_INTERSECTION` | AABB intersection test between two objects |
| `GET_SPATIAL_REPORT` | Spatial summary for one object: bounds, nearby objects |
| `CAST_RAY` | Ray cast from `origin=[x,y,z]` in `direction=[dx,dy,dz]` |
| `VERIFY_ASSEMBLY` | Rule-based checks: `must_touch`, `parent_must_be` |
| `DETECT_GEOMETRY_ERRORS` | Per-object: non_manifold_edges, boundary_edges, zero_area_faces |
| `GEOMETRY_COMPLEXITY` | Triangle/vertex/ngon counts + complexity tier |
| `CHECK_PRODUCTION_READINESS` | Manifold, UV, materials, naming, origin alignment; score 0–100 |
| `GET_HIERARCHY_TREE` | BFS parent→children tree up to `max_depth` |

### 📸 get_viewport_screenshot_base64

Captures the viewport as a base64 PNG the AI can directly see and reason about.

Key parameters

| Parameter | Example | Description |
|-----------|---------|-------------|
| `view_direction` | `&quot;MULTI&quot;` | `FRONT`, `RIGHT`, `TOP`, `ISOMETRIC`, or `MULTI` (all four) |
| `target_objects` | `[&quot;Arm_L&quot;, &quot;Body&quot;]` | Frame specific objects instead of full scene |
| `gap_focus_m` | `0.002` | Auto-zoom to show a gap of this distance |
| `display_mode` | `&quot;MATERIAL&quot;` | `SOLID`, `MATERIAL`, or `WIREFRAME` |
| `action` | `&quot;SMART_SCREENSHOT&quot;` | Automatically picks the best view |

---

## Tool Tier System

The AI context window would overflow if all 69 tools were listed in full detail every time. The tier system solves this:

| Tier | Priority | Count | Format in `list_all_tools` |
|------|----------|-------|---------------------------|
| **ESSENTIAL** | 1–9 | 9 | Full detail — title, description, all parameters |
| **CORE** | 10–49 | ~35 | Compact table row |
| **STANDARD** | 50–149 | ~20 | Compact table row |
| **OPTIONAL** | 150+ | 4 | Listed last (external integrations) |
```python
# Filter by intent — reduces 69 tools to ~15 relevant ones (77% fewer tokens)
list_all_tools(intent=&quot;rig a character&quot;)
list_all_tools(intent=&quot;physics simulation&quot;)
list_all_tools(intent=&quot;export to Unity&quot;)

Supports English, Turkish, and French intent keywords.


Key Features

Assembly Intelligence

get_scene_graph ANALYZE_ASSEMBLY gives a full integrity report:
- BVH surface-gap measurement — actual vertex-to-face distance, not just bounding-box
- INTERPENETRATION detection — BVH face overlap, not just AABB
- Hierarchy-aware pairs — always tests parent↔child; skips distant objects to avoid O(N²)
- Production readiness score 0–100 — manifold geometry, UV maps, materials, naming, origin alignment

Thread Safety

All bpy calls from the TCP socket thread are automatically marshalled to Blender's main thread via bpy.app.timers. This prevents EXCEPTION_ACCESS_VIOLATION crashes that occur when background threads touch the Blender API.

Multilingual Intent Routing

list_all_tools(intent=&quot;...&quot;) accepts keywords in English, Turkish, and French. The intent router maps your description to tool categories and returns only the relevant subset — dramatically reducing context window usage.

Visual Verification

get_viewport_screenshot_base64 captures the viewport and returns it as base64 the AI can see:
- Multi-view in one call: FRONT, RIGHT, TOP, ISOMETRIC
- gap_focus_m — zoom precisely to the scale of an assembly gap
- target_objects — frame specific parts, not the whole scene


Testing

Tests run without Blender — bpy is mocked with unittest.mock.MagicMock.```bash
uv run pytest tests/unit -q # 499 unit tests, ~1.4s
uv run pytest tests -v --tb=short # Full suite
uv run pytest tests -v --cov=blender_mcp # With coverage report
uv run python scripts/quality/run_checks.py --fast # 8 quality checks
uv run python scripts/quality/run_checks.py # 12 quality checks


Coverage map — 17 test files

| Module | Test File | Tests |
|--------|-----------|-------|
| 8 ESSENTIAL handlers | `test_essential_tools.py` | 183 |
| `core/parameter_validator.py` | `test_parameter_validator.py` | 60 |
| `core/intent_router.py` | `test_intent_router.py` | 35 |
| `core/execution_engine.py` | `test_execution_engine.py` | 31 |
| `dispatcher.py` | `test_dispatcher_deep.py` + `test_dispatch_routing.py` | 51 |
| `core/semantic_memory.py` | `test_semantic_memory.py` | 25 |
| `core/job_manager.py` | `test_job_manager.py` | 25 |
| `core/response_builder.py` | `test_response_builder.py` | 21 |
| `core/protocol.py` | `test_protocol.py` | 17 |
| `core/error_protocol.py` | `test_error_protocol.py` | 13 |
| Project structure | `test_smoke.py` | 10 |
| MCP bridge validation | `test_engine.py` | 9 |
| `handlers/manage_history.py` | `test_manage_history.py` | 9 |
| `core/security.py` | `test_security.py` | 6 |
| Geometry center computation | `test_scene_graph_geo_center.py` | 6 |
| **Total** | **17 test files** | **499** |

See tests/TESTS.md for full documentation.

---

## Developer Guide

Environment setup```bash
uv sync --all-extras          # Install all dependencies

Quality gates```bash
make check # 12 checks: lint + format + type-check + tests
make check-fast # 8 checks: lint + custom checks
make test-fast # Unit tests only, stop on first failure


Tool inspection```bash
make inspect-summary        # Compact table of all 69 tools
make inspect-essential      # ESSENTIAL tier full detail
uv run python scripts/inspect_tools.py --tool get_scene_graph
uv run python scripts/inspect_tools.py --cat animation

Adding a new handler

Create a file in blender_mcp/handlers/ with @register_handler. Auto-discovered — no list to update.```python
from ..dispatcher import register_handler

@register_handler(
"manage_my_feature",
actions=["CREATE", "DELETE", "LIST"],
schema={
"type": "object",
"properties": {
"action": {"type": "string", "enum": ["CREATE", "DELETE", "LIST"]},
"name": {"type": "string"},
},
"required": ["action"],
},
category="scene",
priority=60, # 1-9=ESSENTIAL, 10-49=CORE, 50-149=STANDARD, 150+=OPTIONAL
description="STANDARD — Create, delete, and list my features.",
)
def manage_my_feature(action, **params):
if action == "CREATE":
return {"created": params.get("name")}
elif action == "LIST":
return {"items": []}


Scripts reference

See scripts/SCRIPTS.md for comprehensive documentation of every script.```bash
python -m blender_mcp --help        # Quick CLI overview
python -m blender_mcp --list-tools  # List all tools
python -m blender_mcp --status      # Project health

Project Structure

Click to expandBlender_mcp/ ├── blender_mcp/ Blender addon (installs via ZIP) │ ├── __init__.py Addon entry + BlenderMCPServer + N-panel UI │ ├── __main__.py python -m blender_mcp CLI │ ├── dispatcher.py Handler registry + dispatch_command │ ├── __version__.py Single source of version truth │ ├── handlers/ 52 handler modules │ │ ├── manage_scene_comprehension.py get_scene_graph (11 actions) │ │ ├── manage_rendering.py RENDER_FRAME, screenshot │ │ ├── manage_scripting.py execute_blender_code │ │ ├── manage_agent_context.py GET_PRIMER, GET_TACTICS │ │ ├── manage_history.py Session checkpoints │ │ ├── get_local_transforms.py Parent-relative coordinates │ │ ├── polyhaven_handler.py Polyhaven CC0 assets │ │ ├── sketchfab_handler.py Sketchfab 3D models │ │ ├── hunyuan_handler.py Hunyuan3D AI generation │ │ ├── hyper3d_handler.py Hyper3D Rodin AI generation │ │ └── ... 40+ more handlers │ └── core/ │ ├── protocol.py Wire protocol (4-byte header + JSON) │ ├── thread_safety.py Main-thread routing via bpy.app.timers │ ├── execution_engine.py Safe bpy.ops + ExecutionPolicy │ ├── parameter_validator.py Type coercion + schema validation │ ├── intent_router.py Multi-language intent classification │ ├── semantic_memory.py Tag-based object resolution │ ├── security.py High Mode / Safe Mode │ ├── job_manager.py Async subprocess queue │ ├── response_builder.py Structured response format │ └── error_protocol.py 280+ ErrorCode enum values ├── stdio_bridge.py MCP bridge (runs outside Blender) ├── scripts/ │ ├── SCRIPTS.md Full scripts documentation │ ├── inspect_tools.py Tool catalog inspector │ ├── count_tools.py Handler count audit │ ├── sync_version.py Version synchronization │ ├── test_blender_imports.py Runtime import validation (needs Blender) │ ├── remove_unused_ignores.py mypy cleanup helper │ └── quality/ │ ├── run_checks.py Quality gate (8–12 checks) │ ├── check_version.py Version consistency │ ├── check_forbidden.py Fatal Blender 5.x pattern scanner │ ├── check_handler_completeness.py Registry audit │ ├── check_handler_imports.py Import style validator │ ├── check_schemas.py JSON schema validator │ ├── check_tool_groups.py Tool group integrity │ └── lint_imports.py Import architecture rules ├── tests/ │ ├── unit/ 499 unit tests (17 files, no Blender needed) │ ├── integration/ 24 mock + live integration tests │ └── TESTS.md Test suite documentation ├── docs/ │ └── ARCHITECTURE.md System design, wire protocol, thread model ├── create_release_zip.py Builds the addon ZIP for Blender ├── Makefile Developer shortcuts ├── pyproject.toml Build + lint + type-check config └── LICENSE MIT License


Contribution Guidelines

  1. Use @register_handler decorator on all handlers — no exceptions
  2. @ensure_main_thread on any handler that calls bpy
  3. No bpy.types.SimpleNamespace — not available in Blender 5.x
  4. No eval/exec outside the execute_blender_code security layer
  5. Use MCPLogger / get_logger() instead of print()
  6. Run make check before committing — all 12 checks must pass
  7. Add unit tests for new logic in tests/unit/

Log Files

Component Windows macOS / Linux
Addon (Blender side) %TEMP%\blender_server_debug.log /tmp/blender_server_debug.log
Bridge (MCP side) %TEMP%\mcp_bridge_debug.log /tmp/mcp_bridge_debug.log

License

MIT License — © 2026 GÖKSEL ÖZKAN

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Blender MCP E4d00a34 怎么安装?

在客户端按下面的安装命令接入:uv run pytest tests/unit -q。装完在客户端配置里引用同一个包或端点。

Blender MCP E4d00a34 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Blender MCP E4d00a34 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Blender MCP E4d00a34 需要 API Key 吗?

资料标注需要会话登录认证,使用前准备好对应凭据,并按最小权限配置。

Blender MCP E4d00a34 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、Windsurf、VS Code;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Blender MCP E4d00a34 能提供哪些能力?

资料显示约 9 个工具;能力标签包括 3D建模、Python、Claude、AI控制。具体工具清单以官方文档为准。

Blender MCP E4d00a34 需要什么运行环境?

运行时为 Python;属于本地进程,需要在本机装好运行环境。

Blender MCP E4d00a34 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。