Quantum-Inspired Supply Chain MCP Server

Quantum-inspired supply chain optimization delivered as an MCP server — connect Claude, Cursor, or any MCP client to 8 advanced analysis tools that pull from 17 live data sources simultaneously. Built for supply chain analysts, risk managers, and compliance teams who need to move beyond spreadsheet-based risk models to real algorithmic intelligence.

Each tool applies a distinct computational method: tensor train MPS decomposition for network flow optimization, correlated hypergraph percolation for cascade failure simulation, VF2 subgraph isomorphism for sanctions circumvention detection, N-player newsvendor Bayesian games for supplier competition, and multivariate Generalized Pareto Distribution fitting for climate tail risk. No coding required — ask your AI assistant and get structured results.

What data can you access?

Why use Quantum-Inspired Supply Chain MCP Server?

Manual supply chain risk assessment means pulling trade data from COMTRADE, cross-referencing sanctions lists, searching corporate registries, checking weather alerts — and doing it all in separate tabs with no way to correlate signals. That process takes a specialist analyst 2-3 days per supply chain segment and still misses the non-obvious cascade risks.

This MCP server automates all 17 data collection calls in parallel, then applies computational algorithms — tensor decomposition, graph percolation, game theory — to surface patterns no manual review could find. Your AI assistant gains the ability to answer "what happens to my semiconductor supply chain if the top 3 Taiwan suppliers fail simultaneously?" in a single tool call.

• Standby mode — the server stays warm and responds in seconds, not minutes; no cold-start delays for time-sensitive queries
• API access — trigger analysis from Python, JavaScript, or any HTTP client using the Apify API
• Spend controls — set a maximum spend limit per session so tool call costs stay within budget
• Monitoring — get Slack or email alerts when runs fail or produce unexpected results
• Integrations — connect to Zapier, Make, or custom webhooks to trigger supply chain analysis on schedule

Features

• Tensor train (MPS) decomposition — sequential SVD truncation factorizes the supply network into core matrices connected by bond dimensions, revealing latent dependencies not visible in raw trade flow data
• Multi-commodity flow optimization via LP relaxation — minimizes total cost subject to flow conservation and capacity constraints using projected gradient descent on the Lagrangian dual; identifies bottleneck edges at capacity saturation
• Correlated hypergraph percolation — models shared commodity group failures as hyperedge correlated failures rather than independent edge failures; Monte Carlo estimation of giant component fraction across 1,000 simulation runs by default
• Critical percolation threshold p_c via binary search — pinpoints the exact failure probability at which the network fragments from one connected component into many isolated islands
• VF2 subgraph isomorphism for sanctions circumvention — state space tree search with feasibility pruning matches 5 evasion pattern templates (shell company chains, nominee structures, layered ownership, jurisdiction hopping, beneficial owner concealment) against the live corporate ownership graph
• N-player newsvendor Bayesian game — Nash equilibrium computed via inverse CDF of log-normal demand using Beasley-Springer-Moro rational approximation; Monte Carlo profit simulation with demand splitting across all identified supplier players
• Price of Anarchy quantification — measures efficiency loss between Nash equilibrium total order and social optimum, showing how much supplier competition degrades supply chain performance
• Multivariate GPD climate tail risk — fits GPD parameters (xi shape, sigma scale) via method-of-moments on exceedances above threshold from 4 hazard data sources; computes tail dependence coefficient chi for co-occurrence of extreme events across locations
• 100-year return period estimation — F(x) = 1 - (1 + xi*x/sigma)^(-1/xi) applied to each supply node location to quantify extreme event exposure
• Algebraic connectivity (Fiedler value) resilience — computes lambda_2 of the graph Laplacian via power iteration with deflation; higher values indicate networks that require more simultaneous failures before fragmenting
• Composite resilience grade A-F — weighted formula R = 0.4norm(lambda_2) + 0.35p_c + 0.25*(1/rank) combining three independent structural measures
• MERA hierarchical coarse-graining — multi-scale entanglement renormalization identifies nodes that remain critical across multiple scales of the network hierarchy, not just locally
• Contingency routing with cost impact — reroutes flows around disrupted nodes to nearest active alternatives and computes exact cost increase percentage and infeasible demands
• 17 data sources called in parallel — all actor calls use Promise.all for sub-timeout concurrent execution; typical tool call completes in 3-5 minutes

Use cases for supply chain risk analysis

Export control and sanctions compliance

Compliance officers running export control programs need to verify that every tier of their supply chain is free of OFAC-blocked entities and sanctions circumvention structures before filing EAR/ITAR paperwork. Manual registry searches miss layered ownership. identify_sanctions_circumvention runs VF2 subgraph matching against live OFAC, OpenSanctions, OpenCorporates, GLEIF, and UK Companies House data simultaneously, returning circumvention risk scores and matched evasion pattern types with ownership chains.

Semiconductor and critical minerals supply chain mapping

Procurement teams managing critical component supply need to understand which geographic nodes carry the most concentration risk. optimize_tensor_network_flow builds the full network from UN COMTRADE bilateral flows and corporate data, runs tensor train decomposition to find latent dependencies, and solves multi-commodity flow to show which nodes are bottlenecks. A query like "rare earth neodymium China Japan" returns the full supplier-manufacturer-distributor graph with capacity and flow data.

Disruption scenario planning and business continuity

Risk managers preparing business continuity plans need to know what a Tier 1 supplier failure actually propagates to. detect_disruption_cascade takes specific trigger nodes and runs 1,000 Monte Carlo hypergraph percolation simulations to estimate how many downstream nodes fail and at what cascade depth. It identifies critical nodes whose removal causes maximum systemic damage — the information needed to prioritize redundancy investments.

Climate physical risk assessment for ESG reporting

ESG teams and insurance underwriters need quantified physical climate risk for each facility in the supply chain. assess_climate_vulnerability fits multivariate GPD to NOAA, USGS, GDACS, and FEMA exceedances at each node location and produces per-node risk tiers (LOW/MEDIUM/HIGH/CRITICAL) with 100-year return period estimates and tail dependence coefficients for correlated multi-location disaster scenarios.

Supplier negotiation and market structure analysis

Category managers entering supplier negotiations benefit from understanding the theoretical Nash equilibrium order quantities and how much supplier competition degrades supply efficiency. simulate_supplier_game identifies suppliers from trade and corporate data, computes each player's optimal order quantity under log-normal demand uncertainty, and quantifies the Price of Anarchy — the gap between competitive equilibrium and social optimum.

Infrastructure monitoring and chokepoint prioritization

Operations teams managing global logistics need a ranked list of the nodes that, if lost, would do the most damage to the overall network. monitor_critical_chokepoints combines four signals — betweenness centrality, MERA persistence across scales, cascade failure impact, and algebraic connectivity contribution — to produce a consolidated chokepoint ranking with system risk summary.

How to connect this MCP server

Step 1: Get your Apify API token

Go to Apify Console and copy your API token. You will need it in the connection URL.

Step 2: Add to your MCP client

Claude Desktop — add to claude_desktop_config.json:

{
  "mcpServers": {
    "quantum-supply-chain": {
      "url": "https://quantum-inspired-supply-chain-mcp.apify.actor/mcp?token=YOUR_API_TOKEN"
    }
  }
}

Cursor — add to your Cursor MCP settings under ~/.cursor/mcp.json:

{
  "mcpServers": {
    "quantum-supply-chain": {
      "url": "https://quantum-inspired-supply-chain-mcp.apify.actor/mcp?token=YOUR_API_TOKEN"
    }
  }
}

Windsurf / Cline / any MCP-compatible client — use the same URL pattern.

Step 3: Start a query

Ask your AI assistant: "Use the quantum supply chain server to assess the semiconductor supply chain for Taiwan and Korea — identify key chokepoints and disruption risks."

The server calls up to 17 data sources in parallel and returns structured results.

Tool reference

optimize_tensor_network_flow

Builds a supply network from all 17 data sources. Applies tensor train MPS decomposition via sequential SVD truncation to expose latent supply chain structures. Solves multi-commodity flow via LP relaxation with projected gradient descent on the Lagrangian dual.

Input parameters:

Cost: $200-300 per call. Calls 17 actors in parallel.

---

detect_disruption_cascade

Simulates cascading failures through the network using correlated random hypergraph percolation. Runs Monte Carlo estimation of giant component fraction and computes critical percolation threshold p_c via binary search.

Input parameters:

Cost: $200-300 per call.

---

identify_sanctions_circumvention

Detects sanctions evasion patterns using VF2 subgraph isomorphism. Matches 5 known evasion pattern templates against the live corporate ownership graph built from OpenCorporates, UK Companies House, GLEIF LEI, OFAC, and OpenSanctions.

Input parameters:

Cost: $150-250 per call. Calls 8 actors.

---

simulate_supplier_game

N-player newsvendor Bayesian game simulation. Computes Nash equilibrium via inverse CDF of log-normal demand with Beasley-Springer-Moro rational approximation. Monte Carlo profit simulation with demand splitting. Measures efficiency loss (Price of Anarchy).

Input parameters:

Cost: $100-200 per call. Calls 5 actors.

---

assess_climate_vulnerability

Fits multivariate GPD parameters (xi, sigma) via method-of-moments to exceedances from NOAA, USGS, GDACS, and FEMA data. Computes tail dependence coefficient chi for multi-location co-occurrence risk. Returns per-node risk tiers and 100-year return period estimates.

Input parameters:

Cost: $150-250 per call. Calls 8 actors.

---

compute_resilience_score

Three-measure composite resilience: (1) algebraic connectivity lambda_2 via power iteration with deflation, (2) percolation threshold p_c from hypergraph Monte Carlo, (3) tensor train rank. Formula: R = 0.4norm(lambda_2) + 0.35p_c + 0.25*(1/rank). Returns grade A-F.

Input parameters:

Cost: $200-300 per call. Calls 17 actors in parallel.

---

plan_contingency_routing

Solves optimal multi-commodity flow for the current network, then reroutes all flows around the specified disrupted nodes to nearest active alternatives. Computes exact cost increase and identifies demands that become infeasible after disruption.

Input parameters:

Cost: $200-300 per call. Calls 17 actors in parallel.

---

monitor_critical_chokepoints

Full pipeline: betweenness centrality (BFS-based), MERA hierarchical coarse-graining for scale-free structure detection, cascade failure impact scoring, and algebraic connectivity resilience. Nodes flagged as chokepoints at multiple analysis levels are ranked highest.

Input parameters:

Cost: $250-400 per call. Full analysis pipeline.

Output examples

optimize_tensor_network_flow — example output

{
  "nodeCount": 142,
  "edgeCount": 387,
  "tensorTrainRank": 8,
  "truncationError": 0.0023,
  "bondDimensions": [4, 8, 8, 6, 4, 4, 3, 2],
  "hyperedgeCount": 31,
  "flowOptimization": {
    "totalCost": 284700,
    "feasible": true,
    "bottleneckCount": 7,
    "topBottlenecks": [
      { "edge": "TSMC_Hsinchu -> Samsung_Pyeongtaek", "utilization": 0.97 },
      { "edge": "Shanghai_Port -> Rotterdam_Port", "utilization": 0.94 },
      { "edge": "Shenzhen_Foxconn -> Apple_Distribution_US", "utilization": 0.91 }
    ]
  },
  "nodes": [
    { "id": "TSMC_Hsinchu", "type": "manufacturer", "country": "TW", "capacity": 10000 },
    { "id": "Samsung_Pyeongtaek", "type": "manufacturer", "country": "KR", "capacity": 7500 },
    { "id": "Kaohsiung_Port", "type": "port", "country": "TW", "capacity": 15000 }
  ]
}

detect_disruption_cascade — example output

{
  "triggerNodes": ["TSMC_Hsinchu"],
  "affectedNodeCount": 67,
  "cascadeDepth": 5,
  "percolationThreshold": 0.42,
  "giantComponentFraction": 0.73,
  "systemicDisruptionRisk": 0.81,
  "criticalNodes": [
    { "id": "Kaohsiung_Port", "removalImpact": 0.64 },
    { "id": "Shanghai_Distribution_Hub", "removalImpact": 0.58 },
    { "id": "Samsung_Pyeongtaek", "removalImpact": 0.51 }
  ],
  "networkSize": 142
}

identify_sanctions_circumvention — example output

{
  "circumventionRisk": 0.78,
  "patternsDetected": 3,
  "patterns": [
    {
      "matchedNodes": ["Nexus Global BVI Ltd", "Nexus Trading HK", "Pinnacle Tech SZ"],
      "patternType": "shell_company_chain",
      "confidence": 0.89,
      "ownershipChain": ["Nexus Global BVI Ltd -> Nexus Trading HK -> Pinnacle Tech SZ"],
      "riskScore": 0.91
    }
  ],
  "suspiciousEntities": ["Nexus Global BVI Ltd", "Pinnacle Tech SZ"],
  "networkSize": 94
}

compute_resilience_score — example output

{
  "overallResilience": 0.61,
  "grade": "C",
  "algebraicConnectivity": 0.34,
  "percolationThreshold": 0.44,
  "tensorRank": 8,
  "weakPoints": [
    { "node": "Taiwan_Strait_Shipping", "contribution": -0.18 },
    { "node": "TSMC_Hsinchu", "contribution": -0.14 }
  ],
  "networkSize": 142,
  "edgeCount": 387
}

Output fields reference

How much does it cost to run supply chain analysis?

This MCP server uses pay-per-event pricing — you pay a fixed amount per tool call. The cost covers all underlying data actor calls.

You can set a maximum spending limit per session in your MCP client configuration. The server checks the charge limit before each tool call and returns a clear error message if the limit is reached rather than continuing to charge.

These tools are priced for professional use — a full supply chain risk assessment session using 4-5 tools runs $700-1,200. Compare this to specialized supply chain risk platforms (Resilinc, Riskmethods, Everstream Analytics) that charge $30,000-100,000+ per year in SaaS subscriptions. With this server you pay only for the analyses you run.

How Quantum-Inspired Supply Chain MCP Server works

Phase 1: Parallel data collection

Every tool call fires up to 17 Apify actor calls concurrently via Promise.all. Actors run with 256MB memory and a 180-second timeout each. Data sources cover the full supply chain intelligence stack: UN COMTRADE trade flows, SAM.gov and USAspending procurement, five corporate registries, two sanctions databases, four natural hazard feeds, two financial data sources, and three geospatial sources. Each actor returns structured JSON items that the scoring engine can consume directly.

Phase 2: Network construction

buildSupplyNetwork() ingests all 17 actor result arrays and constructs a typed supply graph of SupplyNode and SupplyEdge objects. Nodes are typed as supplier, manufacturer, distributor, retailer, port, or hub. Nodes carry capacity, reliability, sanctioned flag, disaster exposure, and climate risk attributes derived from the source data. The network also computes tensor train decomposition immediately: the adjacency-weighted capacity matrix is factorized via sequential SVD with a rank-4 truncation, yielding bond dimensions, truncation error, and MPS core matrices stored in TensorTrainFactor.

Phase 3: Algorithmic analysis

Each tool applies its specific algorithm to the constructed network:

• Flow tools call solveMultiCommodityFlow() which implements LP relaxation: minimize sum(c_ij * f_ij^k) subject to flow conservation at every internal node and capacity constraints on every edge. Solved via 200 iterations of projected gradient descent on the Lagrangian dual with step size 1/(iteration+1).
• Cascade tools call detectDisruptionCascade() which seeds disruption at trigger nodes, propagates via BFS with each hop drawing from a Bernoulli distribution parameterized by edge weight and base propagation probability. Monte Carlo across N runs estimates the giant component fraction. Binary search on propagation probability finds p_c where giant component fraction first drops below 0.5.
• Sanctions tool calls identifySanctionsCircumvention() which constructs a directed ownership graph, generates 5 evasion pattern templates as subgraph templates, and runs VF2 state-space tree search with semantic feasibility pruning (sanctioned-node adjacency constraints) to find isomorphic matches.
• Climate tool calls assessClimateVulnerability() which, for each network node, collects co-located hazard event magnitudes, identifies exceedances above a rolling threshold, and fits GPD (xi, sigma) via method-of-moments. The tail dependence coefficient chi is estimated from bivariate extreme co-occurrence across node pairs.
• Resilience tool calls computeResilienceScore() which builds the n×n graph Laplacian L = D - A, then runs power iteration with deflation to find the Fiedler vector and lambda_2. Combined with p_c and 1/rank in the weighted composite formula, it produces the 0-1 resilience score and maps it to letter grades.
• MERA tool calls computeMERA() which iteratively coarse-grains the network by contracting lowest-weight edges into super-nodes, recording node counts, edge counts, and renormalized weights at each level until fewer than 4 nodes remain. Scale invariance is measured as the ratio of coarse-to-fine edge weight standard deviations.

Phase 4: Result assembly

All tools return structured JSON via the json() helper which wraps results in MCP CallToolResult format. Output includes raw computed values, ranked lists truncated to top-10, and human-readable summaries. The spending limit guard runs synchronously before each analysis: if Actor.charge() returns eventChargeLimitReached: true, the tool exits immediately with a clear error message.

Tips for best results

1. Start with optimize_tensor_network_flow for any new supply chain. The network it builds is representative of the full data state. Use the returned node IDs as inputs for subsequent tools — feeding exact node IDs as trigger_nodes or disrupted_nodes produces more precise results than letting the tools pick defaults.

2. Use identify_sanctions_circumvention before any supplier onboarding decision. The VF2 algorithm matches patterns that manual OFAC searches miss because they span multiple ownership layers. An entity_name input focused on the specific supplier significantly improves match precision.

3. Tune propagation_probability for your industry. The default 0.3 (30% propagation per edge) suits moderately connected supply chains. For tightly integrated just-in-time automotive supply chains, try 0.5-0.7. For commodity supply chains with many alternative suppliers, try 0.1-0.2.

4. Pair detect_disruption_cascade with plan_contingency_routing. Run cascade analysis first to identify which trigger nodes cause the highest affectedNodeCount. Then feed those same nodes as disrupted_nodes to the contingency routing tool to get the exact cost impact and alternative routes.

5. For climate assessment, always specify region. Narrowing from a global query to "Southeast Asia" or "Taiwan Strait" focuses NOAA, USGS, GDACS, and FEMA data pulls on relevant events and significantly improves GPD fit quality.

6. Use simulate_supplier_game before contract renegotiation. The Nash equilibrium quantities and Price of Anarchy figure give you leverage: if the game shows suppliers are over-ordering by 40% relative to social optimum, you have a quantitative basis for coordinated purchasing proposals.

7. monitor_critical_chokepoints is the highest-cost but most comprehensive tool — best used periodically (weekly or monthly) rather than on every query. Run the lighter compute_resilience_score for routine monitoring and reserve the full chokepoint analysis for strategic reviews.

Combine with other Apify actors

Limitations

• All data sources are public. Private supplier contracts, internal capacity data, proprietary logistics pricing, and non-public corporate ownership records are not accessible. The network represents publicly disclosed relationships only.
• Tensor train decomposition quality scales with network size. Networks with fewer than 20 nodes produce low-information decompositions. Best results come from queries that return 50+ distinct entities.
• Monte Carlo percolation converges slowly for very large networks. At 1,000 simulation runs (default), confidence intervals on p_c are approximately ±0.03. For higher precision, increase monte_carlo_runs to 5,000-10,000, which increases run time proportionally.
• VF2 subgraph isomorphism has exponential worst-case complexity. Mitigated by semantic feasibility pruning, but very dense ownership graphs with 200+ nodes may not return all matches within the 180-second actor timeout.
• GPD climate tail estimation requires sufficient extremes. For regions with sparse NOAA/USGS/GDACS records, method-of-moments GPD fits will have high uncertainty. The model flags these with wide confidence intervals.
• Geospatial coverage is uneven. OSM POI and OpenChargeMap have dense coverage in North America, Europe, and East Asia; coverage in sub-Saharan Africa, Central Asia, and parts of South America is sparse.
• Exchange rate and financial data reflects point-in-time values. Flow cost calculations use rates at query time; historical scenario analysis requires separate calls with different temporal parameters.
• This server does not render JavaScript-heavy corporate websites. It uses structured API data from the 17 wrappers, not web scraping. Some private subsidiary relationships published only in PDF annual reports will not be captured.

Integrations

• Zapier — trigger weekly supply chain resilience scoring on a schedule and post results to a Slack channel or Google Sheet
• Make — build automated workflows that run sanctions circumvention screening on new supplier records from your ERP system
• Google Sheets — export chokepoint rankings and climate vulnerability scores to a shared team dashboard
• Apify API — call the MCP server programmatically from Python or JavaScript pipelines in your risk management platform
• Webhooks — receive alerts when specific supply chain actors return unexpected results or error rates spike
• LangChain / LlamaIndex — integrate the MCP server as a tool in multi-step AI agent workflows for autonomous supply chain monitoring and reporting

Troubleshooting

Spending limit reached error on first call. The MCP server checks the charge limit before executing any analysis. If you see "Spending limit reached", go to your Apify account billing settings and increase the run spending limit, or remove the limit for the active session.

Tool call times out after 180 seconds. Each underlying actor has a 180-second timeout. If all 17 actors complete in time but you see a timeout at the MCP transport layer, increase the client-side request timeout. For queries with very broad geographic scope, individual actor calls may hit their own limits — try a more specific query to reduce result set sizes.

Empty or very small network returned. If nodeCount is under 10, the query returned too few entities to build a meaningful network. Try a more specific query that includes company names, country codes, or commodity HS codes (e.g., "HS 8542 integrated circuits Taiwan TSMC" rather than just "chips").

Sanctions circumvention risk near 0 for a known high-risk entity. The VF2 matching runs against publicly disclosed corporate structures. If the beneficial ownership is concealed in a non-public registry jurisdiction (e.g., certain Delaware LLCs or Cayman structures not in OpenCorporates), it will not appear. Use the result as one signal among several, not a definitive clearance.

Climate GPD shape parameter xi returns negative values. Negative xi (bounded Pareto) is a valid GPD outcome indicating the hazard distribution has a finite upper bound. It is not an error — it means the location's extreme event distribution is thin-tailed. Check returnPeriod100yr for the practical risk estimate.

Responsible use

• All 17 data sources accessed by this server are publicly available government databases, international trade organizations, intergovernmental bodies, and open geospatial data.
• Do not use sanctions circumvention screening results as the sole basis for adverse action against any entity without independent legal review.
• Comply with applicable export control regulations (EAR, ITAR, EU Dual-Use Regulation) when using trade flow data for compliance purposes.
• Respect the terms of service of all underlying data providers (OFAC, OpenSanctions, UN COMTRADE, UK Companies House, OpenCorporates).
• For guidance on web scraping and data use legality, see Apify's guide.

FAQ

How does this MCP server differ from a standard supply chain risk platform like Riskmethods or Everstream? Traditional SaaS platforms provide dashboards with pre-modeled risk scores. This server gives your AI assistant direct access to live data and runs algorithmic analysis on demand — you can query any supply chain globally, not just your configured supplier list. The tradeoff is that you need an MCP-compatible client (Claude, Cursor, etc.) and you pay per analysis rather than a fixed subscription.

What is a tensor train (MPS) decomposition and why does it matter for supply chains? Tensor train decomposition factorizes a high-dimensional supply network tensor into a chain of lower-dimensional core matrices connected by bond dimensions. It reveals latent structural dependencies — groups of suppliers and buyers that are coupled through shared commodity flows — that are not visible in direct adjacency analysis. The truncation error tells you how much information was lost in the approximation.

What is the MERA algorithm and what does scale invariance mean in supply chain context? MERA (Multi-scale Entanglement Renormalization Ansatz) is a hierarchical coarse-graining method from quantum physics. Applied to supply chain networks, it iteratively merges lowest-weight edges into super-nodes to reveal which nodes remain structurally significant across multiple scales. A high scale invariance score means the network has a self-similar structure — the same nodes that are central locally are also central globally. These are the highest-priority chokepoints.

How accurate is the VF2 sanctions circumvention detection? Accuracy depends on the completeness of the corporate registry data. For entities with disclosed ownership in OpenCorporates, UK Companies House, or GLEIF, the VF2 matching against 5 evasion pattern templates has high recall. For beneficial owners concealed in non-reporting jurisdictions, recall is limited by what is publicly disclosed. The confidence field on each pattern reflects the structural match quality, not the probability that evasion is actually occurring.

How many supply chain queries can I run per month? There is no query limit — you pay per tool call. A typical supply chain risk assessment session covering 4-6 tool calls costs $800-1,500. If you are running regular automated monitoring, set a monthly spending limit in your Apify account to control total costs.

Is it legal to use this data for sanctions compliance screening? All 17 data sources are publicly available. OFAC and OpenSanctions data is published explicitly for compliance use. Corporate registry data from OpenCorporates and UK Companies House is public record. Using public data for compliance screening is legal and encouraged. For specific legal advice about your compliance program, consult your legal counsel.

How long does a typical tool call take? Tools that call 17 actors in parallel (optimize, cascade, resilience, routing, chokepoints) typically complete in 3-7 minutes depending on data source response times. Tools calling 5-8 actors (supplier game, sanctions, climate) typically complete in 1-4 minutes. The server runs in Apify Standby mode so there is no cold-start delay.

Can I feed the output of one tool into another tool in the same conversation? Yes, and this is the recommended workflow. Use the node IDs returned by optimize_tensor_network_flow as inputs to detect_disruption_cascade and plan_contingency_routing. Your AI assistant can chain these calls automatically if you describe the end goal.

What does a resilience grade of C mean? The grade maps to the composite resilience score: A (0.8-1.0), B (0.6-0.79), C (0.4-0.59), D (0.2-0.39), F (0-0.19). A grade C means the network has moderate resilience — it can tolerate random failures but has identifiable structural weak points. The weakPoints array shows which specific nodes most reduce the score.

Does this server work with any MCP client or only Claude? The server implements the standard MCP protocol (streamable HTTP transport at /mcp) and works with any MCP-compatible client: Claude Desktop, Cursor, Windsurf, Cline, or any custom client using the @modelcontextprotocol/sdk. The connection URL format is the same across all clients.

Can I schedule this server to run supply chain monitoring automatically? Yes. Use Apify's scheduling feature to trigger the actor on a schedule, or use webhooks and the Apify API to integrate with external scheduling systems. You can also set up Zapier or Make workflows to run specific tool calls on a weekly basis and push results to Slack, Google Sheets, or your risk management system.

What happens if one of the 17 underlying actors fails during a call? Each actor call is wrapped in a try-catch that returns an empty array on failure. The network construction and algorithmic analysis proceed with whatever data was successfully retrieved. If critical sources (like OFAC or COMTRADE) return empty, the results will be lower quality but the tool will not crash. The actor logs record which sources succeeded and which failed.

Help us improve

If you encounter issues, you can help us debug faster by enabling run sharing in your Apify account:

1. Go to Account Settings > Privacy
2. Enable Share runs with public Actor creators

This lets us see your run details when something goes wrong, so we can fix issues faster. Your data is only visible to the actor developer, not publicly.

Support

Found a bug or have a feature request? Open an issue in the Issues tab on this actor's page. For custom supply chain analysis solutions or enterprise integrations, reach out through the Apify platform.