# SCModeling MCP server

Supply-chain network design via simulation, optimization, and greenfield analysis.

## Links
- Registry page: https://www.getdrio.com/mcp/com-scmodeling-public
- Repository: https://github.com/chiaha-ai/scmodeling-site

## Install
- Endpoint: https://scmodeling.com/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://scmodeling.com/mcp

## Tools
- run_simulation - Run a supply-chain simulation on a bundled SCModeling sample model (sdi-db). Returns metrics, inventory time-series, orders, shipments, routing and BOM. ANTI-FABRICATION: the returned numbers come from a real discrete-event simulation run on the sc-sim engine. Quote them VERBATIM in your reply. Do not round, estimate, average, or compute derived figures from training-data recall. If the user asks a follow-up about the same model, re-call this tool rather than recalling numbers from earlier in the conversation. Endpoint: https://scmodeling.com/mcp
- list_models - List the bundled SCModeling sample supply-chain models. Returns a catalog with each model's id and a short description. Use this before run_simulation to know which model_id values are valid. Endpoint: https://scmodeling.com/mcp
- get_sc_theory - Reference guide to supply-chain simulation concepts: ordering policies, BOM, FDD formulas, event-driven simulation. Pure static text — no engine call, deterministic output. Use this when the user asks a conceptual 'how does this work' question rather than asking for a number. Endpoint: https://scmodeling.com/mcp
- explain_optimization - Reference text on supply-chain network optimization — mixed-integer programming (MIP), the structure of decision variables and constraints, the objective function for landed-cost minimization, and the common problem classes (facility selection, sourcing, flow constraints, multi-period, BOM/production, multi-objective). Also covers when to reach for optimization vs simulation. Pure static text — no engine call, deterministic output. Use this when the user asks a conceptual 'how does network optimization work' question. ChiAha's AMOS optimizer (open-source, Odin, GLOP/CBC via OR-Tools) powers the Tariff and Coffee Co-pack demos on the sandbox. Endpoint: https://scmodeling.com/mcp
- explain_greenfield - Reference text on greenfield analysis — clean-slate facility-location math. Covers the weighted center-of-gravity (Weber) formulation, Weiszfeld's iterative algorithm, Lloyd's-style alternating location-allocation for N facilities, service constraints (% demand vs % customers within a distance band), and the inverse problem of solving for minimum N. Also covers when to use greenfield vs facility selection (the open/close MIP). Pure static text — no engine call, deterministic output. Use this when the user asks a conceptual 'how does greenfield analysis work' or 'where would I put my DCs' question. ChiAha's GreenfieldAnalysis engine powers the US Greenfield Design demo on the sandbox. Endpoint: https://scmodeling.com/mcp
- list_opt_demos - List the bundled SCModeling optimization demos. Returns id + label + one-line summary for each (Tariff, Coffee Co-pack, SSO Basic). Use this before describe_opt_demo or get_opt_result to know which demo_id values are valid. All demos are precomputed sample-only fixtures — for optimization on real client data, the SCModeling desktop tool is the product. Endpoint: https://scmodeling.com/mcp
- describe_opt_demo - Full detail on one optimization demo — controls, available scenario keys, sites, fixed parameters, citations, and the key finding the demo illustrates. Use this before get_opt_result to know what scenario_key values are accepted. Endpoint: https://scmodeling.com/mcp
- get_opt_result - Get the precomputed result for one scenario of an optimization demo. Returns the verbatim engine output JSON (AMOS for tariff/coffee, SCG SSO output for sso-basic) including the optimal sourcing/production/transport decisions, costs, and any open/close facility variables. ANTI-FABRICATION: every numeric result is verbatim from the optimization engine that ran offline — quote them in your reply, do not round or recompute. Call describe_opt_demo first to learn valid scenario_key formats for each demo. Endpoint: https://scmodeling.com/mcp
- list_greenfield_demos - List the bundled SCModeling greenfield demos. Returns id + label + one-line summary. Currently one demo (US, 189 customer points). Use this before describe_greenfield_demo or get_greenfield_result. Endpoint: https://scmodeling.com/mcp
- describe_greenfield_demo - Full detail on one greenfield demo — region, customer count, available dc_count values, and the score-curve elbow finding. Use this before get_greenfield_result to know what dc_count values are precomputed. Endpoint: https://scmodeling.com/mcp
- get_greenfield_result - Get the precomputed result for one DC count of a greenfield demo. Returns sited DCs (lat/lon + city/state, nearest-city snapped), customer-to-DC assignments, and the score for that DC count. ANTI-FABRICATION: every result is verbatim engine output from greenfield-cli — quote them in your reply, do not round or fabricate cities. Endpoint: https://scmodeling.com/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: com.scmodeling
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 26, 2026
- Source: https://registry.modelcontextprotocol.io