Skip to main content
Pascal exposes a hosted Model Context Protocol server that lets an AI agent create, inspect, edit, validate, and save 3D building projects. Changes use the same project store as the browser editor, so you can watch the result and continue editing it in Pascal. For projects stored by the local Pascal CLI, pascal editor starts MCP automatically. Configure a local client once to launch pascal mcp connect; no hosted account or API key is required. Jump to local MCP. The hosted endpoint is:

​
Create an API key

  1. Sign in and open Settings.
  2. In API keys, enter a name and choose the personal or organization workspace.
  3. Click Create and copy the key immediately. Pascal does not show it again.
  4. Open Connect an AI agent and choose your client for a copy-ready command.
Use a key created by the same Pascal user or organization that owns the projects you want the agent to edit. Agent self-registration creates a separate account, so its projects do not automatically appear in your current browser account.
Treat the API key like a password. Keep it out of source control, chat transcripts, screenshots, and shell history. Revoke a key from Settings when it is no longer needed.

​
Connect your client

Replace paste_key_here with the key you just created.

​
Codex CLI

Start a new Codex session after adding the server.

​
Claude Code

​
Cursor or another mcp.json client

Add this server to .cursor/mcp.json or your client’s equivalent configuration:
Prefer an environment-variable or secret-store interpolation supported by your client instead of committing a literal key.

​
OpenClaw

​
Start an agent session

Ask the client to connect to Pascal and read the pascal://agent-guide resource first. That guide describes the expected project workflow, semantic construction tools, validation, saving, and final handoff. A reliable first request is:
Agents should return the editorUrl produced by Pascal tools rather than constructing a URL themselves. Open that URL to inspect the browser-visible draft.

​
What MCP exposes

The server provides:
  • Tools for projects, rooms, walls, openings, levels, roofs, furniture, scene queries, measurements, validation, collision checks, saving, and version status.
  • Resources for the agent guide, current scene, scene summary, constraints, and a small built-in item catalog.
  • Prompts for building from a brief, iterating from feedback, and renovations from photos when the client supports MCP sampling.
Use semantic tools such as create_room, add_door, add_window, and furnish_room before reaching for raw scene patches. Finish with validate_scene, verify_scene, save_scene, and get_project_status.

​
Hosted MCP, local CLI, and the MCP package

These entry points share the same tools but use different project stores:

​
Local MCP with the Pascal CLI

Start Pascal normally. The editor and authenticated MCP service start together on collision-free loopback ports:
The MCP service is already running. MCP clients use a stable stdio connector so their configuration does not contain the dynamic port or Pascal’s private local token:
For a JSON-based client:
The setup command uses each client’s official CLI and never overwrites an existing Pascal entry. The connector discovers the running service and starts Pascal automatically when it is stopped. Use pascal mcp status, pascal mcp config, or pascal doctor to inspect the integration. A typical existing-project workflow is list_scenes → load_scene → semantic editing tools → validate_scene and verify_scene → save_scene → get_project_status. The returned editorUrl opens the same local project. Use the standalone @pascal-app/mcp package directly only when embedding Pascal tools in another application or providing a custom scene store.

​
Troubleshooting

  • Unauthorized — create a new key, confirm the Bearer prefix, and verify that the client actually sends the header.
  • The project is missing in the browser — confirm that the key belongs to the same user or organization you opened in Pascal. Self-registered agents own a separate workspace.
  • The browser looks stale or empty — ask the agent to call get_project_status, load the correct project, save a draft, and return the reported editorUrl.
  • A session expired — reconnect the MCP client, then call get_project_status with the project ID to bind the new session.
  • Photo tools fail — vision tools require an MCP client that supports sampling.
For direct HTTP integrations, use the OpenAPI document. MCP clients should use the native Streamable HTTP endpoint instead of reimplementing MCP over OpenAPI.