All plugins

Official

Blender

Official Blender Lab MCP server over stdio, pinned to upstream v1.0.3, with a Blender workflow skill. Needs Git and uv; Blender 5.1+ is not needed at install. The skill opens Blender itself when a task needs it and, after you agree, installs Blender and Blender Lab's MCP add-on. First startup downloads Python dependencies; prepare the uv environment before connecting. Disclosure — tools execute arbitrary Python in Blender with your privileges; the skill starts Blender with online access for that session only (your saved preference is unchanged), and the add-on's local server on port 9876 has no password, so any program on this computer can use it while Blender is open; only after you agree does the skill download Blender from download.blender.org (about 400 MB, about 1.5 GB unpacked), check it against blender.org's sha256 list and install it in your own folder without administrator rights (Linux ~/.local/opt, macOS ~/Applications, Windows %LOCALAPPDATA%\Programs\Blender Foundation; never over an existing Blender), and download the v1.0.3 add-on, check its hash and install or enable it; first start downloads the pinned Blender Lab MCP server and its Python dependencies with uv. Server discovery does not prove scene readiness.

NousResearch592Toolsv0.4.1Updated 11 days ago

About

Official Blender Lab MCP server over stdio, pinned to upstream v1.0.3, with a Blender workflow skill. Needs Git and uv; Blender 5.1+ is not needed at install. The skill opens Blender itself when a task needs it and, after you agree, installs Blender and Blender Lab's MCP add-on. First startup downloads Python dependencies; prepare the uv environment before connecting. Disclosure — tools execute arbitrary Python in Blender with your privileges; the skill starts Blender with online access for that session only (your saved preference is unchanged), and the add-on's local server on port 9876 has no password, so any program on this computer can use it while Blender is open; only after you agree does the skill download Blender from download.blender.org (about 400 MB, about 1.5 GB unpacked), check it against blender.org's sha256 list and install it in your own folder without administrator rights (Linux ~/.local/opt, macOS ~/Applications, Windows %LOCALAPPDATA%\Programs\Blender Foundation; never over an existing Blender), and download the v1.0.3 add-on, check its hash and install or enable it; first start downloads the pinned Blender Lab MCP server and its Python dependencies with uv. Server discovery does not prove scene readiness.

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. If none is found, the skill offers to install the newest official release from download.blender.org into your own folders (no administrator rights), checked against blender.org's sha256 list. Blender 5.1+ has no build for Intel Macs or Linux on ARM.
  • The official Blender Lab MCP add-on in Blender. The skill offers to install it (the pinned v1.0.3 extension, through Blender's own command line), in the same question when it also installs Blender, or walks you through the official page.
  • Hermes opens Blender itself when a task needs it, with --online-mode so the add-on can start its bridge on loopback port 9876 without changing your saved preferences. A Blender you open yourself needs Allow Online Access turned on for the bridge to start.
  • 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; the skill opens Blender when a task needs it, and installs Blender or the add-on only after you agree.

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.

README from the reviewed commit 9b11ffe; it updates when the author re-pins.

More by NousResearch

26 plugins by NousResearch in the catalog.

NousResearchaccent-pickerOKLCH 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.OfficialDesktop app592NousResearchadvanced-delegationTwo extra delegation modes for `delegate_task`, next to the built-in default. Model routes (`delegation.backend: model_map`): the agent picks a named model route per subagent from a list you define (e.g. fast, deep, local). Profile routes (`delegation.backend: profile_routes`): the agent runs a subagent as one of your Hermes profiles, with that profile's own model, credentials, skills and SOUL.md. Only route names and their one-line descriptions reach the model. Adds `hermes delegation config` (pick the mode and edit its routes; `--show` prints the setup) and the `/delegation` slash command (save a mode for the next session, or `--now` to apply it to the current chat). Needs Hermes 0.22.5 or newer, the first release with pluggable delegation providers; Hermes 0.22.0 to 0.22.4 refuses to install it, and on a core older than 0.22.0 it installs, logs one warning and does nothing. Disclosure — no Python dependencies and no network or model calls of its own; subagents run through core's `delegate_task` on the routes you configured. Writes only `delegation.backend` and `delegation.backends.*` (model_map / profile_routes) in the active profile's config.yaml, through core's config writer. A model route's optional `api_key` is stored in config.yaml in plain text (`provider:` keeps keys in .env / auth.json). Listing a profile under profile routes lets this profile's subagents use that profile's credentials, SOUL.md and terminal policy.Officialtools592NousResearchagent-importers`hermes import-agent`: import an OpenClaw (~/.openclaw, or legacy ~/.clawdbot / ~/.moltbot), Claude Code (~/.claude), Codex CLI (~/.codex), Cursor (~/.cursor), Grok Bot (a self-export the Bot writes from a prompt the importer prints) or OpenBot desktop (its openbot.db) setup into Hermes in one command; always previews first and asks before applying. Claude Code / Codex / Cursor: instructions, Cursor rules and memories become memory entries, Bash permission rules become command allow/deny lists, MCP servers land in config.yaml, skills are copied, and `--sync` re-imports sources that changed. OpenClaw (core's former `hermes claw migrate`; the plugin keeps that spelling, `hermes claw cleanup` and the openclaw-migration skill): persona, memories, skills, model and messaging settings, MCP servers and agent behaviour. Formerly built into Hermes core; `hermes setup` offers to install it when it finds one of these agents, and profiles with a registered sync source are migrated automatically. Disclosure — no Python dependencies, no network calls and no model calls. Claude Code / Codex / Cursor: reads those agents' local config trees (never their credential files; secret-looking MCP env vars and headers are stripped and listed) and writes only into the active profile (memories/MEMORY.md with a backup, config.yaml, skills/ and import-sync.json). OpenClaw: reads the OpenClaw dir (openclaw.json, its .env, workspace files such as SOUL.md / MEMORY.md / USER.md, skills); API keys and bot tokens come over only with --migrate-secrets (allowlisted names, shown in the preview). It writes into the active profile (config.yaml, .env, SOUL.md, memories/, skills/openclaw-imports/, a migration/openclaw/<time>/ report with item backups, and a backups/pre-migration-*.zip restore point), plus a workspace dir only when --workspace-target names one. It runs local pgrep / systemctl / tasklist checks to warn when OpenClaw or a Hermes gateway is still running, and `hermes claw cleanup` renames the OpenClaw dir to *.pre-migration after a confirmation. Grok Bot / OpenBot: instructions become SOUL.md, memories and user facts become memory entries, skills land in skills/<source>-imports/, scheduled routines become paused cron jobs (--activate-routines to start them) and event routines a notes file; credential-looking export keys refuse the file, and secret MCP env vars and headers are stripped and listed. OpenBot's database is opened read-only (or read from a scratch copy that is deleted after the read).Officialtools592NousResearchbubblewrapBubblewrap terminal backend for Linux: every terminal and execute_code command runs in its own bwrap sandbox on this machine at the host's own paths, with a read-only root, a writable working directory (per profile: restricted, workspace or network), the dot entries of the home directory (credential stores always) and the Hermes home hidden, private temp and process directories, agent and docker sockets masked, and per-command memory, CPU and process limits (`hermes config set terminal.backend bubblewrap`). Disclosure — no Python dependencies and no network calls of its own: it runs your commands through the `bwrap` and `prlimit` binaries you install (bubblewrap, util-linux), and under the default `network` profile those commands share the host network. It reads no credentials. File tools (read_file, write_file, patch, search_files) run inside the sandbox too, and because the working directory is a real host directory Hermes keeps its dangerous-command prompts, as for the local backend.Officialtools592
All 26 by NousResearch