An MCP connection for controlling a Massing building and construction project from an AI agent. MCP is a way for an agent to call a project's data and analysis tools.

Use it to view projects, records, shared project files, key performance indicators, and model checks; run compliance, schedule-risk, carbon, permit, and drawing-quality analyses; create IFC building models; and draft RFIs.

It lets the agent work from the project's actual records and applies the same permissions, validation, safeguards, and audit trail as the web and HTTP interfaces.

massing-bim — Skill for Claude Code and Codex by ibuilder

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add ibuilder/massing --skill mcp-skills

Clone the repo

git clone --depth 1 https://github.com/ibuilder/massing

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ibuilder/massing/mcp-skills.svg)](https://agentmods.dev/skills/ibuilder/massing/mcp-skills)

Your own site

<a href="https://agentmods.dev/skills/ibuilder/massing/mcp-skills"><img src="https://agentmods.dev/badge/skills/ibuilder/massing/mcp-skills.svg" alt="Measured on agentmods" height="20"></a>

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,137 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00090	$0.01137
Opus 5	$0.00045	$0.00568
Sonnet 5	$0.00018	$0.00227
Haiku 4.5	$0.00009	$0.00114

Measured 7d ago against content hash 58ae9cc0f342, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

massing-bim scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/mcp-skills/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Massing over MCP

Massing exposes an offline-first MCP server (services/api/mcp_server.py) that lets you drive a real project through the same engines the web UI and HTTP API use — every read is grounded in the project's own data and every write goes through the identical validation, guardrail, and audit path. You never guess from memory; you call a tool and report what it returns.

Connect

pip install "mcp[cli]"
cd services/api
PYTHONPATH=src DATABASE_URL=postgresql://… python mcp_server.py     # stdio server

Claude Desktop (claude_desktop_config.json):

{ "mcpServers": { "massing": {
    "command": "python",
    "args": ["/path/to/services/api/mcp_server.py"],
    "env": { "PYTHONPATH": "/path/to/services/api/src",
             "DATABASE_URL": "postgresql://user:pass@host/db",
             "AEC_RBAC": "1", "AEC_MCP_USER": "[email protected]" } } } }

Set AEC_MCP_USER to the acting identity when AEC_RBAC=1: reads are then scoped to that user's member projects and write tools require editor role — the agent can never do what the person couldn't.

Tools

Tool	Kind	What it does
`list_projects`	read	projects you can see (id + name)
`project_snapshot`	read	cross-module status: RFIs, submittals, COs, punch, safety, schedule + budget KPIs, risk headline
`list_records`	read	records of any module (`rfi`, `submittal`, `information_container`, `schedule_activity`, …)
`cde_status`	read	ISO 19650 CDE container discipline
`bim_kpi_scorecard`	read	the 10-category BIM KPI scorecard
`openbim_quality`	read	LOIN / IDS / export-health / bSDD (needs a loaded model)
`standards_check`	read	run `iso19650` \| `cobie` \| `ids` \| `uniclass` — clause-referenced findings + a readiness score
`list_recipes`	read	the authoring-coverage matrix — every recipe `run_recipe` can drive, by category + IFC output
`schedule_risk`	read	Monte Carlo P10/P50/P80/P90 completion, criticality index, delay drivers
`carbon_report`	read	A1–A3 embodied carbon per element + Buy Clean limits + LEED inventory (needs a model)
`permit_readiness`	read	submission-readiness over egress + approvability + code analysis + sheet coverage (needs a model)
`drawing_qa`	read	drawing-set QA — duplicate/gap numbers, titleblock, issuance hygiene, model cross-checks
`create_rfi`	write	create an RFI
`run_recipe`	write	drive a GUID-stable authoring recipe (add_wall, add_column, set_pset, …), saving an audited version

Read the full file on GitHub · 78 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 78 lines · 90 tokens per session scan A 58ae9cc0f342

Subscribe to this mod's changes

massing-bim is a skill published in the GitHub repository ibuilder/massing (134 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 1,137 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metrics Project management aec bcf bim bim-viewer construction ifc

ara3d-sdk

Use when processing AEC/BIM 3D data in .NET 8 — mesh generation and transformation, SIMD-accelerated math, IFC/STEP/PLY to glTF/GLB/VIM conversion, plugin development. Ara3D-SDK: high-performance .NET 3D geometry and BIM library suite.

znlgis/opengis-skills · 70 tokens

elements

Use when generating building information models (BIM) programmatically in C#/.NET — wall, beam, column, floor creation, geometry kernel (BREP/CSG), glTF/IFC/JSON serialization, MEP systems, spatial grids. Hypar Elements: the smallest useful BIM — a cross-platform C# library for creating building elements without…

znlgis/opengis-skills · 81 tokens

construction-expert

Expert-level construction management, project planning, BIM, safety compliance, and construction technology. Use when the user mentions BIM, project management, safety, or building, or when the task involves Construction Management, Technologies, Standards and Regulations, or Cost Control.

personamanagmentlayer/pcl · 54 tokens

massing-bim