Blender Optics Simulator runs on your own machine — the client starts it, so there is no endpoint to ping. 89 installs a week from pypi. Last commit 21 Sep 2026.
Build, align & render a real optical bench in Blender; drivable by an AI agent over MCP.
We read the source, 9 h ago · rules 3dff92dd89df
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
subprocess.Popen([bpy.app.binary_path, path], close_fds=True)
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
__import__(name)
subprocess.Popen([bpy.app.binary_path, path], close_fds=True)
zip_path = os.path.join(ROOT, "dist", zip_name)
post_top=p.z-drop
if bottom-4>post_top:
G._cyl(prefix+'PlatformStem_'+tag,4,bottom-4-post_top,(p.x,p.y,(bottom-4+post_top)/2),coll,'steel')
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add blender-optics-simulator -- uvx blender-optics-mcp
{
"mcpServers": {
"blender-optics-simulator": {
"args": [
"blender-optics-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.blender-optics-simulator]
command = "uvx"
args = ["blender-optics-mcp"]
{
"mcpServers": {
"blender-optics-simulator": {
"args": [
"blender-optics-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"blender-optics-simulator": {
"args": [
"blender-optics-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
OPTICS_BRIDGE_PORT (TCP port of the add-on's localhost bridge inside Blender (Optics > Simulation > Start MCP Bridge).), OPTICS_BRIDGE_HOST (Host of the add-on bridge.).
The author declared them in the registry entry; get the values from the project itself.
Agent-driven search: build, import, tune, search, and score result quality — all over MCP.
Design, fill with real store data, render and publish Store Builder pages from an AI agent.
Generate on-brand images from your AI agent: design, edit, and render templates over MCP.
Flash and run real firmware on physical embedded dev boards from an AI agent, over MCP.
Read-only MCP server for the OPERANT AI operating-agent calibration benchmark.
Query your local super-log bench from an AI agent - read-only log tools over the hub.
Task management your AI agents can actually run. One line becomes a context-ready task over MCP.
A verified dependency-audit verdict any AI agent can call over MCP, not a raw scan.
Answers built from our own checks of this server.