DDC_Skills_for_AI_Agents_in_Construction MCP — Use Cases, Install & Live Demo

Why use it

Key features

Breadth: 221 sub-skills across the construction lifecycle
BIM data handling (IFC parsing, Revit exports, model audits)
Cost estimation templates and WBS conventions
Scheduling helpers (P6/MS Project-adjacent)
Document control: submittals, RFIs, change orders

Live Demo

What it looks like in practice

ddc-skills-for-ai-agents-in-construction-skill.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "ddc-skills-for-ai-agents-in-construction-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction",
        "~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "ddc-skills-for-ai-agents-in-construction-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction",
        "~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "ddc-skills-for-ai-agents-in-construction-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction",
        "~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "ddc-skills-for-ai-agents-in-construction-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction",
        "~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "ddc-skills-for-ai-agents-in-construction-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction",
        "~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "ddc-skills-for-ai-agents-in-construction-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction",
          "~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add ddc-skills-for-ai-agents-in-construction-skill -- git clone https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction ~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use DDC_Skills_for_AI_Agents_in_Construction

How to audit a BIM IFC model for basic data quality

👤 BIM coordinators and VDC teams ⏱ ~60 min advanced

When to use: You receive an IFC file from a consultant and need a quality check.

Prerequisites

Python with ifcopenshell — pip install ifcopenshell
Skill cloned — git clone https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction ~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction

Flow

Parse the IFC

Audit model.ifc — count entities by class, find missing Psets, flag orphan geometry.✓ Copied

→ Entity counts + quality flags
Check naming and classification

Verify wall and room naming against our company standard.✓ Copied

→ Per-element conformance report
Produce a coordinator-ready report

Generate an issue list the consultant can act on.✓ Copied

→ Ordered issue list

Outcome: A model audit report you can send back in under an hour.

Pitfalls

Huge IFC files exceed memory — Stream-parse rather than load full tree; or pre-filter by spatial structure

Combine with: filesystem

Produce a quick order-of-magnitude cost estimate

👤 Estimators, PMs, bid teams ⏱ ~30 min intermediate

When to use: Early-phase numbers for a concept before you commit to a detailed estimate.

Flow

Describe the project

Concrete frame office, ~12,000 sqm, Tier-1 city, shell-only. Give me a per-sqm cost range.✓ Copied

→ Range with the assumptions stated
Break into WBS

Break the estimate into WBS sections with % allocations.✓ Copied

→ Top-level WBS with line items
Flag risks

List the top 5 cost risks for this concept.✓ Copied

→ Risks with impact

Outcome: A defensible concept estimate ready for internal review.

Pitfalls

Using global averages without local adjustment — Always override with local benchmarks when you have them

Review a construction schedule for common issues

👤 Schedulers and PMs ⏱ ~30 min intermediate

When to use: You got a schedule from a subcontractor and need to check for the obvious red flags.

Flow

Feed the schedule

Review schedule.xlsx — flag missing logic, negative float, open ends, and unrealistic durations.✓ Copied

→ Categorized findings
Prioritize

Rank by impact on completion date.✓ Copied

→ Sorted list

Outcome: Quick surface-level schedule review that catches 80% of common problems.

Pitfalls

Missing CPM-level analysis — For real float analysis, export from P6 rather than relying on Excel

Combinations

Pair with other MCPs for X10 leverage

ddc-skills-for-ai-agents-in-construction-skill + filesystem

Process a whole project folder of IFCs, schedules, and docs

Walk project/ and produce a weekly coordination packet.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
bim-audit	IFC path	On any incoming IFC	ifcopenshell compute
cost-estimation	project concept	Early phase	0
schedule-review	schedule export	Sub-submittal review	0
document-control	RFIs/submittals/COs	Project admin	0

Cost & Limits

What this costs to run

API quota: none
Tokens per call: 5–30k per task
Monetary: free at skill level
Tip: Use only the sub-skills relevant to your role — this bundle is wide

Security

Permissions, secrets, blast radius

Credential storage: none

Data egress: none

Construction estimates and schedules are often confidential — handle like other sensitive project data

Troubleshooting

Common errors and fixes

ifcopenshell install fails

Use Python 3.10 or 3.11 and pip install ifcopenshell from a wheel matching your platform.

Verify: python -c 'import ifcopenshell; print(ifcopenshell.version)'

Estimates are wildly off

Override unit costs with your regional database; the skill uses generic benchmarks only

Alternatives

DDC_Skills_for_AI_Agents_in_Construction vs others

Alternative	When to use it instead	Tradeoff
generic csv-data-summarizer-claude-skill	Your construction data is CSV and you don't need BIM semantics	No domain knowledge

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills