scenario-blender — Claude Code skill: what it does, how to install
The scenario-blender skill connects Claude Code and other platforms to an active Blender scene via an MCP server. It enables agents to read scene data and generate 3D assets, materials, or video.
MIT 654 installs ★ 3,964 updated 2026-10-23
npx skills add scenario-labs/skills --skill scenario-blender -a claude-codeWhat scenario-blender does
The skill interfaces with the scenario-blender MCP server running on port 9876. It allows agents to inspect the scene, manipulate camera paths, and trigger the generation of PBR materials, meshes, or environment maps directly from the Blender workspace.
Prerequisites include the Scenario for Blender extension version 5.0 or later. You must enable Allow Online Access in Blender and configure the API key within the extension settings. The authentication token is ephemeral and regenerates upon server restart, requiring an update in your MCP configuration.
What it helps with
- generate PBR materials from selected scene objects
- capture the current viewport as a reference for generation
- animate the scene camera using preset paths
Example prompts for the agent
- Analyze the scene and list all objects using
scene_summary - Capture the viewport as a reference for a new 3D mesh
- Set up an orbit camera path for the current scene
How to install scenario-blender
1Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-blender -a claude-code2Manually: put the files in place
~/.claude/skills/scenario-blender/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/scenario-blender/
1Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-blender -a codex2Manually: put the files in place
.agents/skills/scenario-blender/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-blender -a cursor2Manually: put the files in place
.cursor/skills/scenario-blender/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install scenario-labs/skills skills/scenario-blender2Manually: put the files in place
.github/skills/scenario-blender/SKILL.md1Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-blender -a gemini-cli2Platform CLI
gemini skills install https://github.com/scenario-labs/skills --path skills/scenario-blenderManually: put the files in place
.devin/skills/scenario-blender/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add scenario-labs/skills --skill scenario-blender -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about scenario-blender
How to install scenario-blender in Claude Code?
Run the command npx skills add scenario-labs/skills --skill scenario-blender -a claude-code in your terminal.
What does scenario-blender do?
It links an AI agent to Blender via an MCP server, enabling scene control and 3D asset generation.
What is required to run scenario-blender?
You need the Scenario for Blender extension (5.0+), enabled Allow Online Access, and a valid authentication token.
Source text
SKILL.md · MIT
---
name: scenario-blender
description: "Use when an agent works in an open Blender scene through the Scenario for Blender extension's local MCP server (scenario-blender on 127.0.0.1:9876): connecting Claude Code, Cursor, Claude Desktop or Codex to Blender, the headless scenario_blender command, quoting and generating Scenario images, PBR materials, 3D meshes, video, audio or 360 environments from the scene, capturing the viewport or selected meshes as references, placing saved results, Render Video camera paths, or execute_python."
license: MIT
---
# Scenario for Blender
## Overview
Scenario for Blender is an open-source extension for Blender 5.0 and later, licensed
GPL-3.0-or-later and marked experimental in its
[README](https://github.com/scenario-labs/blender-plugin). Users install it from the extension
repository `https://blender.scenario.com/repo/index.json` (Edit > Preferences > Get Extensions >
Repositories) or from a ZIP on the
[releases page](https://github.com/scenario-labs/blender-plugin/releases); the handbook is
[blender.scenario.com](https://blender.scenario.com/). The Scenario API key and secret live in the
extension's preferences: the agent never handles them. Blender's Allow Online Access must be on.
The extension runs a local MCP server, `scenario-blender`, at `http://127.0.0.1:9876/mcp` (JSON-RPC
over HTTP POST with a bearer token, no SSE). When 9876 is busy it tries the next three ports, so the
URL to use is the one shown in Scenario > Agents (MCP). Scene tools run on Blender's main thread.
Every tool and parameter here comes from the extension's tool reference,
[docs/MCP.md](https://github.com/scenario-labs/blender-plugin/blob/main/docs/MCP.md); `tools/list`
carries each tool's full guidance. Local names are verb-first (`list_models`, `job_status`) and
never interchangeable with the hosted server's (`models_list`, `model_run`, `jobs_wait`). Training,
collection rename or deletion, workflow authoring and usage stay on mcp.scenario.com: see the
`scenario` skill, and connect both servers when a task needs both. Modeling, sculpting, rigging or
shading through bpy is the `scenario-blender-expert` skill's work; exporting for an engine is
`scenario-blender-export`'s. If a sibling skill named here is missing from your available skills,
load it with `skill_get` (Scenario MCP) or ask the user to install it
(https://github.com/scenario-labs/skills#install); unattended, proceed from tool schemas and flag
the gap.
## Setup
The token is generated the first time the server starts in a Blender session, held only in memory,
and changes after every restart: a 401 means it is stale, so copy the setup again from the Agents
(MCP) panel. It is a secret, separate from the API key: never paste it, or a copied snippet, into an
issue, transcript or screenshot. The client must run on the same machine, since `127.0.0.1` is
loopback, and must use that address: another host name returns 403 `forbidden host`.
Claude Code:
```sh
claude mcp add --transport http scenario-blender http://127.0.0.1:9876/mcp \
--header "Authorization: Bearer <token>"
```
Codex:
```sh
export SCENARIO_BLENDER_TOKEN='<token>'
codex mcp add scenario-blender --url http://127.0.0.1:9876/mcp \
--bearer-token-env-var SCENARIO_BLENDER_TOKEN
```
Cursor takes an `mcpServers` entry
`"scenario-blender": {"url": "http://127.0.0.1:9876/mcp", "headers": {"Authorization": "Bearer <token>"}}`.
Claude Desktop goes through the extension's stdio bridge: copy its snippet from the panel, which
fills in the installed shim path, and check that its command points to a working Python 3
interpreter.
Headless, with the extension enabled:
```sh
export SCENARIO_BLENDER_TOKEN='<token>'
blender --background scene.blend --command scenario_blender --port 9876
```
`--online-mode` enables online access for that run. `--token '<token>'` overrides the variable but
exposes the token in process arguments; with neither, the command generates one and prints it once.
Headless, `screenshot_viewport`, `render_still` and every `capture_reference` source except `MESH`
fail: they need the GUI.
## Quick reference
In call order:
| Step | Tool | Notes |
| ---------------- | ------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Read the scene | `scene_summary`, `datablocks_summary`, `object_detail(name)` | Start here; `scene_summary` reports the selection, cameras, frame range and 3D cursor |
| Change the scene | `select_objects(names)`, `set_frame(frame)`, `camera_path` | `camera_path` takes a `preset` (such as `orbit` or `push_in`), a free-text `description` or `waypoints`, plus `duration`, `focal`, `aim_at_subject`; it animates the scene camera for Render Video and generates nothing |
| Look | `screenshot_viewport`, `render_still(source, width, height)` | GUI only; PNG content for the agent, not an upload |
| Reference | `capture_reference(source)`, then `reference_upload_status(context_id, reference_id)` | `source`: `VIEWPORT`, `CAMERA`, `VIEWPORT_CLIP`, `CAMERA_CLIP` or `MESH` (selected meshes as one GLB). Poll until `state` is `imported`, then use its `asset_id` |
| Pick a model | `list_models(lane, query)`, `model_schema(model_id)` | Lanes: `image`, `video`, `3d`, `material`, `audio`, `render_image`, `render_video`, `edit3d`, `panorama`. Ids come from `list_models` each session, never constants |
| Quote | `estimate_cost(model_id, parameters, lane)` | Free dry run; returns `quote_id` and `cu_cost_exact` (a decimal string). `lane` defaults to `image` |
| Generate | `generate(lane, model_id, parameters, quote_id, approved_cost)` | Spends credits. Same lane, model and parameters as the quote; `approved_cost` is the exact string the user approved |
| Wait | `wait_for_job(job_id, timeout)`, `job_status(job_id)` | `timeout` defaults to 45 seconds, inside the 60-second limit many clients apply; go up to 170 only when your client waits longer. Call again while `delivery_active` is `true` |
| Place | `list_local_jobs`, `prepare_result_application`, then `apply_result_application(context_id, application_id)` | Only Image results import by themselves; everything else waits for an approved destination |
| Python | `blender_api_help(path)`, then `execute_python(code)` | Off until the user enables Allow connected agents to run Python |
`upload_reference(path, kind)` sends only a file the user chose in Blender this session or one the
extension saved; any other path is refused, so capture the scene instead or ask the user to pick the
file. Render Image and Render Video take no raw parameters: `render_form` with
`action: "configure"`, then `action: "prepare"` captures and uploads the scene, then `estimate_cost`
and `generate` with `parameters` omitted. The model copies the capture's motion, limbs included: for
characters that must walk or run naturally, block them as capsules (scenario-blender-blockout). A
panorama goes into the World through `prepare_result_application` with `purpose: "world"`.
## Worked example: viewport to a mesh at the 3D cursor
"Turn what I see in the viewport into a 3D prop next to it."
1. `scene_summary`: note `cursor` and confirm a GUI session, since the capture needs one.
2. `capture_reference` with `{"source": "VIEWPORT"}` returns `context_id` and `reference_id`, not an
asset id. Call `reference_upload_status` with both until `state` is `imported`, and keep its
`asset_id`. A scene change before the upload finishes stops it.
3. `list_models` with `{"lane": "3d"}`; pick an image-to-3D entry from its description.
`model_schema` with its `model_id` names the image input; file parameters take Scenario asset
ids.
4. `estimate_cost` with
`{"lane": "3d", "model_id": "<id>", "parameters": {"<image input>": "<asset_id>"}}` returns
`quote_id` and `cu_cost_exact`. Tell the user the cost in CU and stop until they say yes.
Unattended, with nobody to answer, report the quote and stop here: neither this gate nor the one
in step 8 is ever passed without the user.
5. `generate` with the same `lane`, `model_id` and `parameters`, plus `quote_id` and `approved_cost`
set to `cu_cost_exact` verbatim. It returns `local_id`.
6. `wait_for_job` with `{"job_id": "<local_id>"}` (45 seconds by default), again while
`delivery_active` is `true`. The 3D lane stops at saved results: nothing is in the scene yet.
7. `job_status` lists `import_units`; take the `key` of the `primary` unit. `list_local_jobs` gives
`context_id` and this job's `request_id` and `revision`.
8. `prepare_result_application` with
`{"context_id": "...", "request_id": "...", "expected_revision": <revision>, "asset_id": "<key>"}`
captures the current 3D cursor as the destination and returns `application_id`. Show the user the
returned scene, `cursor`, `format` and files, and wait for approval.
9. `apply_result_application` with `context_id` and `application_id` imports one new model group at
that cursor. `scene_summary` confirms it.
## Common mistakes
- `generate` without a fresh `estimate_cost` and the user's yes. A changed lane, model, input, scene
or credential needs a new quote, a quote is used once, and an estimate never authorizes spending
by itself.
- Repeating a timed-out `generate`. Inspect `job_status` or `list_local_jobs` instead; an
unconfirmed submission blocks an identical one until the user marks it reviewed in Blender.
- Passing a file path, or `capture_reference`'s `reference_id`, where a file parameter takes an
asset id.
- Expecting `import_result` to place a result: it only explains the approval flow above.
- Captures in `--background`: only `capture_reference` `MESH` works there.
- Assuming `execute_python` is on. It fails with `PermissionError` naming Scenario preferences
(MCP > Allow connected agents to run Python), off by default: ask the user, and prefer the
specific tools.
- Calling the hosted server's tools (`model_run`, `jobs_wait`, `model_schema_get`) on this server.
- Treating "catalog is still loading" or "model description is still loading" as a failure: nothing
was quoted, submitted or changed, so call again. Missing credentials in the extension's
preferences keep the catalog from loading.
- Assuming the file is saved: no tool saves the `.blend`, so ask the user to save it.
© scenario-labs · MIT · scenario-labs/skills