openmep
OpenMEP
Open MEP building state that a language model can reason about and edit correctly — grounded in deterministic loads and duct sizing, graded by a deterministic checker.
The bet: the useful unit of AI-assisted HVAC design is not a Revit plugin but a small, inspectable data model (rooms, loads, terminals, ducts, connectivity, constraints) that deterministic engines compute over and agents edit. This repo is that model, the engines, and the harness that measures whether an agent can edit it without breaking it.
What is here
Workspace | What it does |
| Dependency-free equal-friction round-duct sizing, supply/return/exhaust network CFM propagation, port-coincidence connectivity, ASHRAE equivalent diameters, and actual-vs-recommended size grading. |
| MCP server ( |
| Sizes and checks HVAC in Pascal Editor scenes, live through Pascal's MCP ( |
| Agent skill (Pascal skills.sh format) that drives the adapter from an MCP-connected agent: gather CFM, set |
| Synthetic T1–T6 mechanical-plan editing benchmark (single + branching fixture sets), deterministic grader, |
| IFC ingestion (web-ifc): storeys, spaces, elements, space boundaries, geometric envelope recovery; 2D plan extraction (Clipper2 footprints); design-day cooling/heating loads (ASHRAE 62.1 ventilation, 90.1 assemblies); mechanical plan layers with CFM-grounded terminals and inferred duct connectivity; plan validator; headless eval runner. |
| Next.js 16 viewer: 3D (That Open / Three.js) and storey-driven 2D plan mode with the load dashboard. |
|
|
Real-model tests and evals run on public IFC fixtures (buildingSMART
Duplex and WBDG Office ARCH + MEP pairs, CC BY 4.0) fetched by
fixtures/fetch-public-ifc.sh; see fixtures/README.md for provenance and the
exporter quirks the pipeline handles. No IFC is committed to this repository.
Related MCP server: AutoCAD MCP Pro
Quick start
Give an agent a duct-sizing tool
claude mcp add openmep -- npx -y -p @openmep/mcp openmep-mcpAny MCP client works ({"command": "npx", "args": ["-y", "-p", "@openmep/mcp", "openmep-mcp"]}).
Describe the system in plain language, with the CFM each terminal needs, and the
agent calls the engine; see packages/mcp/README.md.
Size a duct network from JSON (no editor required)
npx -p @openmep/hvac-domain openmep-hvac size packages/hvac-domain/examples/furnace-two-registers.items.json --pretty
npx -p @openmep/hvac-domain openmep-hvac duct --cfm 250 --role main --diameter-in 6From a checkout: npm ci && npm run build --workspace @openmep/hvac-domain, then
node packages/hvac-domain/bin/openmep-hvac.js ....
The network is a list of equipment, fittings, terminals with engineer-supplied
requiredCfm, and segments linked by connectedItemRefs. The result lists each
run's system, CFM, role, recommended standard round diameter, velocity and friction
rate, grades any existing section as ok/undersized/oversized, and reports
terminals with no airflow or no path to equipment. Any host that can produce this
document gets the same engine; openmep-pascal items produces it from a Pascal
scene.
Check a Manual D worksheet
cd examples/manual-d-demo && npm install && node demo.mjsTakes blower external static, device losses, and one line per run (CFM,
length, fitting equivalent length) and prints available static, total effective
length, the Manual D friction rate, and a round size per run, graded against the
size you already have. Ships with the ACCA worksheet example; see
examples/manual-d-demo/README.md for what it does and does not do.
Try airflow design
Change a room's supply airflow, preview the connected duct sizes on the plan, apply or undo the change, and export the edited plan JSON.
npm ci
npm run dev:design
# Open http://localhost:3001/designRequires Node.js 24+. The first launch fetches the public Office IFC pair and
prepares Level 1; no database, .env, or model credentials are needed. Pass
-- --refresh to rebuild the example, or -- --port 3002 to use another port.
Edits are session-local manual airflow scenarios with round-duct proposals;
export saves the applied plan JSON, not a rewritten IFC. The public example
labels its inferred connections and assumed initial demands. Existing model
viewers also link to Airflow design for their selected storey.
Full viewer and IFC pipeline
npm ci
fixtures/fetch-public-ifc.sh # duplex + wbdg_office (~55 MB)
npm run build --workspace @openmep/hvac-domain --workspace @openmep/agent-benchmark
npm testMaterialize an editable HVAC plan from the public office model:
npm run eval:materialize -- \
--arch fixtures/public/wbdg_office/arc.ifc \
--mech fixtures/public/wbdg_office/mep.ifc \
--model-id wbdg_office
# eval-runs/wbdg_office/Level_1/{architecture,loads,mechanicalVisual2D,mechanicalEdit2D,baseline}.jsonRun the synthetic agent benchmark: npm run benchmark:verify, or see
packages/agent-benchmark/README.md for grading your own candidates.
Web app
Copy
.env.exampleto.env; start PostgreSQL and create the database.npm run db:initnpm run dev:web— seeds the Duplex pair as a stable dev fixture at/models/00000000-0000-4000-8000-000000000001?mode=plan(MEP_SKIP_DEV_FIXTURE=1to skip;IFC_FIXTURE_DIRto relocate fixtures).npm run dev:workerin a second terminal.
Status and limits
Loads are design-day, steady-state (no RTS/CTS lag, latent, or schedules) and not yet validated against a reference case; envelope U-values come from ASHRAE 90.1 prescriptive tables, climate from 15 city anchors. Treat outputs as preliminary sizing inputs, not a sealed design.
Roof loads are zero for Revit exports whose ceilings are room-bounding (all seen so far); plenum inference is open work.
Duct connectivity for exports without
IfcRelConnectsPortsis inferred geometrically and flagged as such on every item.
License
MIT — see LICENSE. Fixture data keeps its upstream licenses (fixtures/README.md).
Release and provenance rules for the npm packages: docs/public-artifact-release.md.
Available Tools
2 toolssize_ductSize one ductARead-onlyIdempotent
Recommend a standard round diameter for one duct run carrying a given CFM, with velocity and friction at that size. Optionally grade an existing round, rect, or oval section as ok, undersized, or oversized.
Inputs: cfm (required), role, existing, airflowType.
size_duct_networkSize a duct networkARead-onlyIdempotent
Size every supply, return, exhaust, and outside-air segment of a connected duct network. Each terminal's requiredCfm is carried along its shortest same-system path to equipment and summed per segment; roles (main/branch/runout) are inferred. Sizes at the fixed default friction rate, or, when fan is given with segment lengthFt and fitting equivalentLengthFt, at the Manual D friction rate derived from available static pressure over the total effective length (returned as design: ASP, TEL, friction rate, longest paths). Returns per-segment recommendations, grades for segments with an existing section, and findings: missing-required-cfm, no-equipment-path, dangling-reference, mixed-system-segment, undersized, oversized, friction-rate-out-of-range, missing-equivalent-length.
Inputs: items (required), fan.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The tools operate at different scopes: size_duct handles a single duct run, while size_duct_network sizes an entire network with multiple segments. The names are similar but the descriptions clearly differentiate their purposes, making confusion unlikely for an agent.
Both tool names follow a consistent verb_noun pattern (size_duct, size_duct_network). The only minor issue is that the noun part is very similar, but the naming convention itself is consistent.
With only 2 tools, the server is quite thin for a duct sizing domain. While each tool is well-scoped, the limited count may force agents to rely on external knowledge for common tasks like equipment selection or duct material properties.
The surface covers core duct sizing operations but lacks obvious complementary tools such as equipment selection, pressure loss calculations for fittings beyond equivalent length, or output formatting. Notably, there is no tool to retrieve or list existing duct networks, which could be a gap for iterative design workflows.
Related MCP Connectors
Heating, ventilation and energy engineering calculations and diagnostics for AI agents.
Design, solve and simulate HVAC systems from real components, weather years and buildings.
Construction takeoff and estimating for AI agents. Measure a drawing PDF, export a priced estimate.
Solar, weatherization, EV charging, battery and heat-pump decision tools for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to draft, read, validate, diff, and take off CAD drawings through a single typed contract served by either a live COM session or a headless ezdxf engine. Ships 247 tools covering P&ID, mechanical, and architectural drafting, with ISO GD&T and dimension-tolerance validation plus spec-to-drawing and takeoff-to-workbook workflows.-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to automate drafting end to end — drawing mechanical parts, P&IDs, and architectural plans, then verifying measurements against source requirements, critiquing quality, and delivering DWG/DXF files. Runs live through COM on Windows or headless anywhere via ezdxf, exposed as typed tool packs so clients only load the capabilities they need.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables agents to generate and locally edit parametric architectural DXF files, run geometry checks and rectangular layout solving, and use traceable research and professional-learning workflows; on Windows it can also attach to a running AutoCAD for guarded read/write operations.6MIT
- AlicenseAqualityCmaintenanceEnables AI agents to run deterministic data-center engineering calculations and commissioning audits, including liquid-cooling hydraulics, pipe friction and flow checks, corrosion severity classification, protocol search, and defect-code lookup.62MIT