Skip to main content

blender

✓ Officialv0.2.0★ 271

Official Blender Lab MCP server over stdio, pinned to upstream v1.0.3, with a Blender workflow skill. Requires Blender 5.1+, its separately installed MCP add-on, Git and uv. First startup downloads Python dependencies; prepare the uv environment before connecting.

Open in Hermes Desktop
hermes plugins install blender

README

From the reviewed commit abec9e8 ↗; it updates when the author re-pins.

Blender integration for Hermes

Part of Hermes Official Plugins, Nous Research's official plugins for Hermes Agent. Formerly NousResearch/hermes-plugin-blender, which is archived; this directory carries its full history.

A portable Hermes plugin containing MCP launch configuration and a workflow skill for the official Blender Lab MCP server.

Install

hermes plugins install blender
hermes plugins enable blender

Choose the destination profile with the global hermes -p <profile> option. Catalog installation by the short name blender becomes available only after its catalog entry is merged and published.

Prerequisites

  • Blender 5.1 or newer on the same machine as the Hermes backend. Hermes checks for it before installing and refuses the install when it is missing: on Windows the Blender uninstall entry's install folder or %ProgramFiles%/Blender Foundation/Blender */blender.exe; on macOS Blender.app in /Applications, ~/Applications or the Steam library; on Linux blender on PATH, the org.blender.Blender flatpak, the blender snap or the Steam library (native or flatpak Steam). Linux has no version source, so the 5.1 minimum is checked on Windows and macOS only. This needs a Hermes release that reads location lists in app: declarations.
  • The official Blender Lab MCP add-on installed and enabled in Blender, with Online access enabled and its bridge started on loopback port 9876.
  • Git and uv available to the backend. Network access is required for the initial MCP environment setup.
  • Optional, for the *_for_cli tools that open a saved .blend file in a separate background Blender: a blender command on the backend's PATH. BLENDER_PATH set in a shell or .env does not reach the server.

See setup and troubleshooting. Installing this package does not install Blender, change Blender preferences, install its add-on, or open a scene.

Prepare the server before first activation

The first upstream download/build took several minutes in our Windows checks. Warm its isolated uv environment before asking Hermes to connect, so a normal MCP connection timeout does not interrupt the download:

uv tool run --from "git+https://projects.blender.org/lab/blender_mcp.git@2cea8d566dde07fbac28a61d698909d69724e853#subdirectory=mcp" blender-mcp --help

Restart Hermes, or use the explicit plugin/MCP reload commands supported by your release. The package's skill is available through skills_list and its qualified name via skill_view. Verify a real get_objects_summary response before treating Blender as ready.

What runs

Hermes launches the official server over stdio with the same pinned source as the preparation command. The MCP server connects to the Blender add-on over 127.0.0.1:9876. No native Hermes Python hooks, tool overrides, desktop JavaScript or self-updater are included.

The upstream revision is fixed to 2cea8d566dde07fbac28a61d698909d69724e853 (v1.0.3). uv resolves its Python dependencies in an isolated tool environment; those transitive dependencies are not fully locked by this package.

Security and licensing

Blender Lab warns that its tools execute arbitrary Python in Blender without protection against file deletion or data exfiltration. Use only with trusted workflows, keep the bridge loopback-only, and prefer a disposable scene or isolated machine for experiments. This is not a sandbox.

This uses Blender Lab's source on projects.blender.org, not the unrelated PyPI package with the same blender-mcp name. Do not substitute an unqualified package install.

The wrapper configuration and original documentation are MIT-licensed. The external Blender Lab server and add-on remain GPL-3.0-or-later, owned by their respective authors. No Blender Lab code is vendored here.

Verified scope

See verification. Headless scene read/create/transform/readback/delete passed on Windows ARM64 and x64 with Blender 5.2.2 LTS. Graphical screenshots, deferred operations and liveness detection (whether Blender and its bridge are running) are not verified or implemented by this wrapper. MCP tool listing alone does not establish scene readiness.

accent-picker✓ Official★ 271

OKLCH accent colour picker for the Hermes Desktop status bar: drag it and the whole theme retints live, with palette commands to reset to the theme default or copy the current colour. A theme-authoring tool; the colour is scratch state and is never persisted. Desktop-only (desktop/plugin.js inside the plugin SDK surface); no agent tools, hooks, middleware or env vars.

Desktop
claude-subscription-directsdk✓ Official★ 271

Experimental model provider that runs Hermes turns on a Claude Pro/Max subscription through the official Claude Code CLI (the Agent SDK path), so no separate API key or per-token bill. Requires the claude CLI installed and logged in; the plugin checks for it at load, in hermes model, in the pickers and before every request, and refuses cleanly with the install hint when it is missing. Disclosure — every turn is billed against your Claude subscription's Agent SDK allowance, and the provider inherits whatever account claude is logged into.

Models
hermes-memory-wiki✓ Official★ 271

Memory Wiki dashboard tab: browsable subject pages and daily logs derived from local session history, plus a read-only Persistent Memory (MEMORY.md / USER.md) audit panel.

Desktop
hermes-telegram-business✓ Official★ 271

Observe-with-approval Telegram Business Mode (secretary bot): every drafted customer reply needs owner approval before it is sent.

Platforms
homeassistant✓ Official★ 271

Home Assistant gateway platform (state-change events in, persistent notifications and cron notify delivery out) plus the homeassistant toolset (ha_list_entities, ha_get_state, ha_list_services, ha_call_service). Formerly built into Hermes core; existing users are migrated automatically.

Platforms
langfuse✓ Official★ 271

Langfuse observability for Hermes: one trace per turn, one generation per LLM call (usage and cost from Hermes' own pricing, cache and reasoning tokens included), one observation per tool call and subagent. Content capture is sanitized by default (metadata-only and full are opt-in); sends traces only to the Langfuse project whose keys you set. Formerly built into Hermes core as observability/langfuse; existing users are migrated automatically.

General

← Back to the catalog · catalog built Oct 14, 2026