Supply Chain Digital Twin
@apifyforge
About Supply Chain Digital Twin
Supply chain digital twin simulation via 8 quantitative algorithms — connect any AI agent to live corporate, trade, sanctions, hazard, and financial data across 17 public data sources.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"supply-chain-digital-twin-mcp": {
"url": "https://ryanclinton--supply-chain-digital-twin-mcp.apify.actor/mcp"
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Supply Chain Digital Twin?
A supply chain digital twin simulation server that connects any AI agent to live corporate, trade, sanctions, hazard, and financial data across 17 public data sources. It turns natural-language supply chain questions into structured risk intelligence using 8 quantitative algorithms from network science, operations research, and econometrics. Built for supply chain risk analysts, operations researchers, and AI agents.
How to use Supply Chain Digital Twin?
Add the server URL to an MCP client configuration (Claude Desktop, Cursor, Windsurf, LangChain, or any MCP-compatible client). The endpoint is https://supply-chain-digital-twin-mcp.apify.actor/mcp with no authentication headers required. Tools such as simulate_disruption_cascade, optimize_logistics_transport, and estimate_supplier_survival are invoked via natural-language queries.
Key features of Supply Chain Digital Twin
- Buldyrev-Parshani-Stanley mutual percolation for cascade failure simulation
- Cross-entropy importance sampling for rare-event risk estimation
- Sinkhorn-Knopp optimal transport for logistics cost minimization
- Tri-level Stackelberg attacker-defender game for adversarial interdiction
- Competing risks Cox proportional hazard model for supplier survival
- Leontief input-output analysis via Neumann series multipliers
- 17 parallel data sources fetched within a single tool call
Use cases of Supply Chain Digital Twin
- Stress-test supplier networks and estimate cascade failure probabilities before board reviews
- Optimize logistics routing and sourcing using entropy-regularized optimal transport
- Identify critical defense supply chain links vulnerable to adversarial attack
- Assess 12-month failure probability of every supplier decomposed by failure cause
- Estimate how a production shock propagates through sectoral input-output networks
- Generate uncertainty-quantified demand forecasts and optimal base-stock inventory policies
FAQ from Supply Chain Digital Twin
What data sources does the server access?
17 public data sources including OpenCorporates, UN COMTRADE, OFAC sanctions, USGS earthquakes, NOAA weather, GDACS disaster alerts, FEMA emergencies, Censys cyber data, OpenAQ air quality, and more — all called in parallel within a single tool.
How are missing geographic coordinates handled?
When supplier coordinates are unavailable, the server falls back to seeded probabilistic assignment: a 15% chance of exposure with a 0.3 weight, using a deterministic pseudo-random number generator for reproducibility.
Is authentication required to connect?
No. The server accepts MCP connections over HTTP without any authentication headers. The Apify token is managed server-side.
Are simulation results reproducible?
Yes. All stochastic components use a string-hash-seeded linear congruential generator, producing identical results across identical inputs.
How does the server handle tool timeouts?
Each actor call within a tool has a 180-second timeout and gracefully returns an empty array on failure, ensuring robustness when a data source is unavailable.
Frequently asked questions
What data sources does the server access?
17 public data sources including OpenCorporates, UN COMTRADE, OFAC sanctions, USGS earthquakes, NOAA weather, GDACS disaster alerts, FEMA emergencies, Censys cyber data, OpenAQ air quality, and more — all called in parallel within a single tool.
How are missing geographic coordinates handled?
When supplier coordinates are unavailable, the server falls back to seeded probabilistic assignment: a 15% chance of exposure with a 0.3 weight, using a deterministic pseudo-random number generator for reproducibility.
Is authentication required to connect?
No. The server accepts MCP connections over HTTP without any authentication headers. The Apify token is managed server-side.
Are simulation results reproducible?
Yes. All stochastic components use a string-hash-seeded linear congruential generator, producing identical results across identical inputs.
How does the server handle tool timeouts?
Each actor call within a tool has a 180-second timeout and gracefully returns an empty array on failure, ensuring robustness when a data source is unavailable.
Basic information
More Other MCP servers
ghidraMCP
LaurieWiredMCP Server for Ghidra
XcodeBuildMCP
cameroncookeA Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
Codelf
unbugA search tool helps dev to solve the naming things problem.
DeepMark
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
Comments