Docs
Download

MCP server

Let AI agents read and build your node trees, and use Blender.

Scripting Nodes has an MCP server. An AI agent connected to it (Claude Code, Codex, Claude Desktop, ...) can build add-ons with nodes in the Blender you have open, see what it built, try it and fix what's wrong. You watch the nodes appear in the node editor and can step in at any time.

The MCP Server panel in the node editor's sidebar with the Start button, setup buttons for Claude Code, Codex, Claude Desktop and JSON, the port and Agents Run Python

Starting it

Open the MCP Server panel in the node editor's sidebar (Scripting Nodes tab) and click Start. It listens on http://127.0.0.1:7423/, only on this computer, and the panel shows Running on :7423. Then connect your agent: the buttons under Copy the setup for copy what it needs, see Claude Code, Codex and Claude Desktop.

SettingWhere
PortPanel and preferences (MCP Server Port)The port it listens on, default 7423. Change it while the server is stopped
Agents Run PythonPanel and preferences (Allow Running Python)Whether agents may run any Python in Blender (run_python)
Start with BlenderPreferencesStarts the server every time Blender starts
TokenPreferencesA password clients have to send with every request. Read when the server starts; the setup buttons include it

The preferences are in Edit › Preferences › Add-ons › Scripting Nodes.

What an agent can do

Build add-ons

Tool
get_addonOverview: name, module, metadata, trees, properties, how many problems. Agents start here
list_node_types, get_node_typeThe nodes by category, what they do, their sockets and settings
create_tree, get_tree, get_nodeTrees and nodes, with their errors and the code they wrote
edit_treeAdd, change, link and delete many nodes in one call
edit_propertiesThe add-on's properties, groups and the properties of operators and preferences
edit_functionThe inputs and outputs of functions (node groups)
make_group, ungroupMove nodes into a new function and call it, or back (like Ctrl G and Ctrl Alt G)
read_text, write_text, edit_scriptsScripts: their code, and which scripts are part of the add-on
edit_assetsFiles and folders the add-on ships with
search_data_pathsBlender data paths for Blender Data nodes
set_addonName, author, tagline, version, permissions and other settings

Check the work

Tool
get_problemsNodes with errors, a build that failed, what the Extensions platform would reject
get_codeThe generated Python, live or as exported
run_operatorRun an operator of the add-on and see what it printed
show_tree, screenshotOpen a tree in the node editor; a picture of Blender as you see it
export_addonThe installable zip, checked against the guidelines

Use Blender

Tool
run_pythonRun any Python in Blender: set up a scene, inspect data, anything the other tools don't cover
undoUndo or redo the agent's last steps (each tool call that changes the file is one step, like Ctrl Z)
get_logsRecent messages of Scripting Nodes and prints of the add-on

Safety

The server only accepts connections from this computer, and refuses requests that come from web pages. With run_python, an agent can run any code in Blender, like the Python console. Turn off Agents Run Python if you don't want that; any program on your computer that can reach the port could use it too. A Token makes the server refuse clients that don't send it.

Agents change the file you have open. Save before you start, and use Ctrl Z or undo to take back what you don't like.