Vectorworks MCP Codex Plugin
Enables AI-powered control and automation of Vectorworks 2024/2025 on Windows via natural language commands through Codex.
README
Vectorworks MCP Codex Plugin
Codex plugin for Vectorworks 2024/2025 on Windows. It packages skills, helper scripts, and an MCP server wrapper for the companion vectorworks-mcp checkout.
Install
/plugin marketplace add BhaveshY/vectorworks-mcp-codex-plugin
/plugin install vectorworks@vectorworks-mcp-codex-plugin
Prerequisites
- Windows with Vectorworks 2024 or 2025.
- PowerShell available on PATH.
- A local checkout of the companion
vectorworks-mcprepository unless the plugin is being run from a repo that already contains the connector sources.
Companion repo override
If the companion checkout is not found automatically, set the canonical override before launching Codex:
$env:VW_MCP_REPO = "C:\path\to\vectorworks-mcp"
VECTORWORKS_MCP_REPO remains supported as a backward-compatible alias by the bundled scripts, but new setup should prefer VW_MCP_REPO.
Use
- Open Vectorworks on the same machine as Codex.
- Use the
setup,diagnose,ping, andworkskills from the plugin root. - The plugin starts the Python MCP wrapper through
plugins/vectorworks/scripts/run-vectorworks-mcp.ps1.
Native bridge status
The repository includes a native Vectorworks SDK bridge scaffold under native_bridge/, but it is not compiled or installed by default. The default bridge remains bridge_kind=python_dialog_agent_session, which keeps CAD API access marshaled through Vectorworks' dialog/event context. Raw socket reachability is not enough to prove CAD API safety.
Why this is not as simple as a Revit-style setup yet
Vectorworks Python scripts run inside the Vectorworks process and CAD API calls must be scheduled on a safe Vectorworks context. A Revit-style connector can usually rely on a mature external-event model; this Vectorworks bridge still needs explicit native SDK build/install steps before it can replace the dialog-agent-session launcher.
Native bridge doctor/smoke examples
Dry-run an explicit native bridge artifact install plan:
powershell -ExecutionPolicy Bypass -File .\scripts\doctor-native-bridge.ps1 -BuiltArtifact C:\path\to\VectorworksMCPBridge.vwlibrary -Install -WhatIf
Install an explicit native bridge artifact after review, then restart Vectorworks:
powershell -ExecutionPolicy Bypass -File .\scripts\doctor-native-bridge.ps1 -BuiltArtifact C:\path\to\VectorworksMCPBridge.vwlibrary -Install
# Restart Vectorworks
Run the native smoke harness after a bridge candidate is listening:
powershell -ExecutionPolicy Bypass -File .\scripts\smoke-native-bridge.ps1 -Phase 1 -PingCount 3 -ReadCount 2
powershell -ExecutionPolicy Bypass -File .\scripts\smoke-native-bridge.ps1 -Phase 0 -Stop -Json
After installing, enable/load the native VectorworksMCPBridge plug-in in Vectorworks, then rerun the doctor. If the scaffold has been copied into a Vectorworks SDK example project, wire-native-bridge-project.ps1 can wire the reviewed bridge sources. The native doctor reports nextCommand, nextCommandReason, and nextCommandSpec plus safety metadata including requiresNetwork, mayInstallSoftware, and rerunDoctorAfter.
Notes
VW_MCP_HOST,VW_MCP_PORT, andVW_MCP_PREFLIGHT_CACHE_MScan tune the MCP wrapper/listener connection.- On Linux CI, PowerShell/Vectorworks-specific tests are skipped; Codex plugin manifest validation is platform-independent.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.