PyNet Bridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PYTHONPATH | No | Path to your src directory |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_active_instancesA | Scans the system for running Autodesk processes with an active PyNet IPC pipe. |
| check_plugin_statusB | Handshake ping to verify the plugin listener is responsive. |
| send_commandB | Direct script execution in the PyNet engine (Target PID, Script Name, Content). |
| send_command_by_pathA | Executes a script file directly by path in the PyNet engine, without sending content inline. |
| get_output_window_statusB | Checks if the output window is currently available/visible. |
| configure_output_windowC | Toggles the visibility of the PyNet log/output window. |
| get_pynet_ui_layoutC | Fetches the full UI structure (ButtonsModules and ScriptButtons). |
| create_pynet_moduleC | Creates a new custom Tab (ButtonsModule) in the Ribbon. |
| delete_pynet_moduleC | Permanently deletes a module and all its contents. |
| get_buttons_dataA | Lists all script buttons for a specific module ID. |
| deploy_script_buttonB | Installs a new ScriptButton into a specific module (Name, Script, Icon, Tooltip). |
| update_script_buttonB | Updates metadata for an existing ScriptButton or moves it to another module. |
| delete_script_buttonB | Permanently removes a ScriptButton from a module by Id. |
| viewer_statusA | Reports whether a PyNet BIM Viewer is open in VS Code (port, package, data dir). |
| viewer_list_clashesA | Reads the loaded package's clashes.json — the data source, NOT the viewer/IFC. Returns each clash with the pnt_id identifiers needed to highlight it. |
| viewer_load_packageB | Loads a .pnt into the open viewer and returns a summary read from clashes.json. |
| viewer_highlight_clashA | Highlights a clash (element(s) A red, element(s) B green) and isolates the rest away. Usually one pnt_id per side (a single clash pair), but either side accepts a list — e.g. one element (A) against every counterpart it clashes with (B), all shown at once. |
| viewer_fitA | Fits the camera to all models in the open viewer. |
| viewer_clearA | Clears highlights and ghosting in the open viewer. |
| viewer_selectA | Highlights a set of elements in the open viewer by pnt_id, in neutral colours (yellow / blue) with nothing else hidden — a plain "look at these" pointer. Pass a list of pnt_ids in |
| viewer_isolateA | Isolates (hides everything except) the given pnt_ids in the open viewer. |
| viewer_isolate_modelsA | Shows only the given model(s)/discipline(s) (by exact name, e.g. "Snowdon Towers Sample HVAC"), hiding every other loaded model. Cheaper than viewer_isolate for "just show me this discipline" requests — no need to resolve every element's pnt_id first. Get the exact model names from viewer_get_state's "models" list. Undo with viewer_clear. |
| viewer_get_stateA | Reads the viewer's last reported state: loaded models and the pnt_id of whatever the user currently has selected (click in the 3D view or the tree panel — null if nothing is selected). Use the returned pnt_id with viewer_get_properties for its details, or feed it into a clashes.json lookup to find what it clashes with. |
| viewer_get_propertiesA | Reads element properties (name, model, psets) from the loaded package's properties.json. Pass one or more pnt_ids to get their full properties (including psets) directly. Called with no pnt_ids, returns a paginated lightweight index (pnt_id, name, model) instead
of every element — narrow it with The data source is the .pnt's properties.json, NOT the viewer or IFC. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 24 tools
The viewer tools overlap heavily: viewer_isolate vs viewer_isolate_models, viewer_select vs viewer_highlight_clash, and viewer_get_properties vs viewer_list_clashes all operate on similar element-visibility/data concepts. The descriptions explicitly cross-reference each other ('use X instead'), which mostly resolves selection, but an agent must read carefully to pick correctly.
All tools use snake_case verb_noun form, which is readable and consistent. There are minor grouping deviations (some tools carry a viewer_ prefix, some a pynet_ prefix, others are bare like send_command or check_plugin_status), but no camelCase/snake_case mixing.
24 tools is on the heavy side for the apparent scope. The UI/module management and IPC scripting areas are reasonably tight, but the viewer control surface alone accounts for eleven tools and could be consolidated.
CRUD for modules and script buttons is largely covered (create/read/update/delete), and the viewer has load, fit, clear, isolate, highlight, select, state, properties, and clash lookup. Minor gaps like no module update/rename and no viewer unload/close keep it from fully complete.