Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add dcc-mcp/dcc-mcp-blender --skill dcc-mcp-blender-setupgit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-blenderWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dcc-mcp/dcc-mcp-blender/dcc-mcp-blender-setup)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-blender/dcc-mcp-blender-setup"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-blender/dcc-mcp-blender-setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-blender/dcc-mcp-blender-setup"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-blender/dcc-mcp-blender-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.01808 |
| Opus 5 | $0.00026 | $0.00904 |
| Sonnet 5 | $0.00010 | $0.00362 |
| Haiku 4.5 | $0.00005 | $0.00181 |
Grade A, and why
dcc-mcp-blender-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dcc-mcp-blender setup
Use this skill when a user wants an agent to prepare a machine so any MCP
host can use dcc-mcp-blender with Blender.
This is an operator skill, not a Blender runtime skill. Do not load it through the Blender MCP server. Run it from the repository checkout or copy its steps into another agent's instructions.
If the user says "帮我参考 dcc-mcp/dcc-mcp-blender/install.md 去安装", read the
root install.md first, then follow this skill.
Goal
End with:
dcc-mcp-blenderand its pip dependencies installed into the target Blender bundled-Python environment.- An MCP host config snippet that points to the Blender MCP server.
- A Blender 5.x-compatible startup bridge that starts the embedded server.
- A live smoke prompt that proves the agent can discover and call Blender tools.
Fast Path
Use the installed adapter lifecycle as the canonical agent path. First resolve the exact Blender executable/application and its target Python interpreter, then inspect the non-mutating plan:
dcc-mcp-blender install --json --dry-run --dcc-path <absolute-blender-path> --python <absolute-python-path>
Review the resolved host, version, profile, interpreter, file steps, and
machine-executable next_steps. If they are correct, execute the same plan and
verify typed readiness:
dcc-mcp-blender install --json --yes --dcc-path <absolute-blender-path> --python <absolute-python-path>
dcc-mcp-blender verify --json --dcc-path <absolute-blender-path> --python <absolute-python-path>
Exit 40 after install means the staged, receipted host integration was
written but host.ping could not yet prove a live Blender instance. Follow the
returned next_steps; do not report the adapter as directly usable yet.
The lifecycle command:
- Probes Blender 3.6+ and the exact target Python before writing.
- Resolves the per-user Blender scripts profile without changing the host installation directory.
- Stages and atomically replaces the owned startup script with rollback.
- Writes an ownership receipt used by
status,verify,upgrade, and receipt-onlyuninstall. - Captures bootstrap failures and verifies a live instance with typed
host.pingrather than a process or port-only check.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 214 lines · 52 tokens per session scan A ca2afec332e5
dcc-mcp-blender-setup is a skill published in the GitHub repository dcc-mcp/dcc-mcp-blender (30 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,808 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
blender-reference-modeling
Build, compare, review, or repair a Blender model against an actual supplied image, photograph, concept, or visual reference using adaptive decomposition, measurable proportions, evidence scoring, and bounded repair. Use only when the request explicitly concerns model creation or quality against visual form criteria…
blender-bridge
Operate Blender Agent Bridge through its stable five-tool MCP gateway for scene inspection, modeling, materials, rigging, animation, simulation, rendering, external assets, trusted scripts, and preview decisions. Use whenever an agent must work in a live Blender scene through Blender Bridge, especially when only…
blender-mcp
Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.
dcc-mcp-core
Foundation library for the DCC Model Context Protocol (MCP) ecosystem. Provides Rust-powered action management, skills system, IPC transport, MCP Streamable HTTP server (2025-03-26 spec, with 2025-06-18 and 2025-11-25 awareness), sandbox security, shared memory, screen capture, USD scene support, and telemetry for…
maya-pipeline
Domain skill — Maya asset pipeline orchestration: set up project directory structures, export scenes to USD, and coordinate multi-step DCC workflows. Use when initialising a Maya project or exporting assets for a downstream pipeline. Not for raw geometry editing — use maya-geometry for that. Not for low-level USD file…
imagemagick-tools
Infrastructure skill — image processing and manipulation via ImageMagick: resize, composite, convert formats, add watermarks. Use when batch-processing textures, thumbnails, or rendered images at the file level. Not for in-DCC texture or material editing — use a domain skill bound to the specific DCC for that.