mcpField
S
Scopture

Scopture

Remote
github.com/ducflairScience & Education0Updated 1d ago
Repository

About Scopture

Scopture provides engineering-focused agent skills, MCP integrations, and automation tools for AI assistants and coding agents. It supports model inspection, drawing reviews, issue management, and tracing technical decisions across project workflows.

Key features

  1. 01Inspect engineering models
  2. 02Review engineering drawings
  3. 03Manage project issues
  4. 04Trace technical decisions

Use cases

  1. 01Inspect CAD/BIM models
  2. 02Review engineering drawings
  3. 03Organize project issues
  4. 04Trace decision rationale

MCP support

The repository includes MCP integrations for Scopture and DUC, but the README does not specify the interfaces they expose.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.scopture.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Agent Skills

Engineering agent skills, Model Context Protocol (MCP) integrations, and automation tools for Scopture and DUC. These skills equip AI assistants and coding agents with domain knowledge to inspect models, review drawings, manage issues, and trace technical decisions across project workflows.

Install

npx skills add ducflair/scopture-plugin --skill duc

Or install all skills from this repository:

npx skills add ducflair/scopture-plugin

Development

# Validate each skill folder
python3 scripts/validate_skills.py

# Test skill discovery
npx skills add . --list

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.