Energy Transition Intelligence MCP Server

Energy transition intelligence for AI agents — this MCP server gives any LLM client access to 7 live data sources and 4 scoring models covering energy transition readiness, grid stress prediction, stranded asset risk, and EV infrastructure gap analysis. Designed for energy investors, grid operators, climate finance teams, utility analysts, and EV infrastructure planners who need structured, quantified intelligence rather than raw data.

The server runs on Apify's infrastructure in persistent Standby mode, so your AI client connects once and gets instant tool responses without cold starts. Each of the 7 tools dispatches parallel queries to real government and open-data APIs, runs the results through purpose-built scoring algorithms, and returns a structured JSON object with scores, grades, signals, and raw evidence — all in a single tool call.

What data can you access?

Why use Energy Transition Intelligence MCP?

Building energy market intelligence from scratch means stitching together 7 different APIs, normalizing incompatible data formats, writing scoring logic, and maintaining it as APIs change. A single analyst doing this manually across multiple regions spends days per assessment. Subscribing to commercial energy data platforms like Wood Mackenzie or BloombergNEF costs $20,000-80,000 per year for comparable coverage.

This MCP automates the entire pipeline. Your AI agent calls one tool, the server fans out to all relevant sources in parallel using Promise.allSettled (so one slow API never blocks the rest), and you get a scored, graded, signal-annotated response in seconds.

• Scheduling — run transition readiness monitoring on weekly or monthly intervals to track regional progress over time
• API access — invoke any tool from Python, JavaScript, Claude Desktop, Cursor, or any MCP-compatible client
• Parallel data collection — all 7 data sources queried simultaneously, not sequentially, minimizing latency
• Monitoring — get Slack or email alerts when grid stress assessments trigger WARNING or EMERGENCY levels
• Integrations — connect results to Zapier, Make, Google Sheets, or your own investment platform via webhooks

Features

• 4 quantified scoring models — Transition Readiness (0-100), Grid Stress (0-100), Stranded Asset Risk (0-100), and EV Infrastructure Gap (0-100) with clearly documented point allocations for each sub-component
• Composite transition grade (A-F) — weighted composite: readiness 30% + inverted grid stress 20% + inverted stranded asset risk 25% + inverted EV gap 25%, producing a single letter grade per region
• 5-tier readiness classification — LAGGING / EARLY / DEVELOPING / ADVANCED / LEADER based on scored thresholds
• Grid stress level classification — NORMAL / WATCH / ADVISORY / WARNING / EMERGENCY, updated dynamically with current weather, time-of-day (peak hours 14:00-19:00 UTC weighted), and seasonal demand cycles
• Carbon intensity benchmarking — scoring calibrated against UK National Grid averages (excellent < 100 gCO2/kWh, average ~200, poor > 300) with peaker plant activation detection at 350+ gCO2/kWh
• Stranded asset risk model — cross-references active NSTA fossil fuel licenses, EIA generation fuel mix (coal, natural gas, petroleum share), Federal Register regulatory tightening signals, and commodity price stress (WTI below $50/barrel, gas below $2.50/MMBtu)
• EV infrastructure gap classification — ADEQUATE / DEVELOPING / UNDERSERVED / SPARSE / DESERT based on charger count, DC fast charger ratio, grid capacity headroom, and EV adoption pressure
• Regulatory signal parsing — scans Federal Register titles for supportive keywords (clean energy, renewable, electric vehicle, emissions reduction) and restrictive keywords (rollback, repeal, deregulat) to compute a net regulatory support score
• Outlook determination — ACCELERATING / ON_TRACK / STALLING / REGRESSING derived from composite of readiness score, grid stress level, and stranded asset exposure
• Opportunity and risk surfacing — each assessment generates a prioritized list of specific investment opportunities and transition risks with quantified thresholds
• Spending limits enforced — every tool call checks Actor.charge() before running, returning a clean error if the per-run budget is reached
• Standby mode deployment — the server runs persistently on Apify, eliminating cold start latency for AI agent workflows
• 7 parallel data sources — EIA, UK Carbon Intensity, Open Charge Map, FRED, Weather Forecast, Federal Register, NSTA dispatched simultaneously per tool call

Use cases for energy transition intelligence

Energy investment and portfolio analysis

Energy investors and asset managers need to compare transition readiness across candidate markets before committing capital to renewable development projects. The assess_transition_readiness tool returns a scored snapshot of renewable generation share, regulatory support level, and EV infrastructure density for any region in seconds. Pair it with evaluate_stranded_asset_risk to identify markets where fossil fuel competitors face accelerating write-down timelines.

Grid reliability planning and operations

Utility operators and grid operators use predict_grid_stress with 48-72 hour weather lookahead to anticipate when extreme heat or cold will spike demand, when low wind speeds will reduce generation capacity, and when peaker plants may be activated. The tool combines current weather forecasts, EIA supply-demand balance, and live carbon intensity to produce a stress level (NORMAL through EMERGENCY) with specific trigger signals — actionable for dispatch planning and reliability reporting.

Climate finance and ESG due diligence

ESG analysts and climate finance teams conducting portfolio reviews need quantified stranded asset exposure across fossil fuel holdings. The evaluate_stranded_asset_risk tool surfaces active oil and gas licenses, generation fuel mix (coal and gas share of total generation), regulatory tightening trajectory from Federal Register publications, and commodity price stress signals from FRED crude oil and gas prices. The result is a 0-100 risk index with MINIMAL through CRITICAL classification.

EV charging network expansion planning

Infrastructure developers and charge point operators identifying underserved markets use analyze_ev_infrastructure_gaps to compare charger density against EV adoption pressure for any city or corridor. The tool classifies markets as ADEQUATE through DESERT and reports total chargers, DC fast charger count, fast charger ratio, and grid capacity headroom — directly supporting site selection decisions.

Carbon reporting and trajectory tracking

Sustainability teams tracking Scope 2 emissions and demonstrating decoupling progress use track_carbon_trajectory to pull grid carbon intensity data, correlate it with generation mix evolution, and surface economic decoupling signals from FRED GDP and emissions series. Output includes average intensity (gCO2/kWh), data point count, and full time-series arrays for downstream analysis.

Energy regulatory intelligence

Policy analysts, lobbyists, and compliance teams monitoring the energy regulatory environment use monitor_energy_regulation to query Federal Register publications by topic and optional geographic focus. The tool classifies retrieved documents by type (proposed rules, final rules, notices), counts them by category, and returns full document records — surfacing emerging policy shifts before they move markets.

How to use energy transition intelligence tools

1. Connect your MCP client — add the server URL https://energy-transition-intelligence-mcp.apify.actor/mcp to Claude Desktop, Cursor, Windsurf, or any MCP-compatible client using the configuration shown below.
2. Choose a tool — ask your AI client to "assess transition readiness for Texas wind energy" or "generate an energy transition brief for the UK". The client selects and calls the appropriate tool automatically.
3. The server runs in seconds — parallel queries fetch live data from up to 7 sources simultaneously. Most tools complete in 15-30 seconds. The generate_energy_transition_brief tool (all 7 sources) typically takes 30-60 seconds.
4. Read scored results — the AI client receives structured JSON with numeric scores, letter grades, named risk levels, and a list of specific signal strings — ready to cite, summarize, or export.

MCP tools

Tool parameters

How to connect this MCP server

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "energy-transition": {
      "url": "https://energy-transition-intelligence-mcp.apify.actor/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_APIFY_TOKEN"
      }
    }
  }
}

Cursor / Windsurf / Cline

Add to your MCP settings:

{
  "energy-transition-intelligence": {
    "url": "https://energy-transition-intelligence-mcp.apify.actor/mcp",
    "headers": {
      "Authorization": "Bearer YOUR_APIFY_TOKEN"
    }
  }
}

Direct HTTP (cURL)

curl -X POST "https://energy-transition-intelligence-mcp.apify.actor/mcp" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_APIFY_TOKEN" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "assess_transition_readiness",
      "arguments": {
        "region": "California",
        "energyType": "solar"
      }
    },
    "id": 1
  }'

Python (via MCP client library)

import asyncio
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

async def assess_region(region: str):
    async with streamablehttp_client(
        "https://energy-transition-intelligence-mcp.apify.actor/mcp",
        headers={"Authorization": "Bearer YOUR_APIFY_TOKEN"}
    ) as (read, write, _):
        async with ClientSession(read, write) as session:
            await session.initialize()
            result = await session.call_tool(
                "generate_energy_transition_brief",
                arguments={"region": region}
            )
            print(result.content[0].text)

asyncio.run(assess_region("Texas"))

Output example

The generate_energy_transition_brief tool returns a comprehensive structured object. Below is a representative output for a mid-transition region:

{
  "region": "Texas",
  "compositeScore": 54,
  "transitionGrade": "C",
  "outlook": "ON_TRACK",
  "transitionReadiness": {
    "score": 61,
    "renewableShare": 34.2,
    "carbonIntensity": 218,
    "evChargers": 11,
    "regulatorySupport": 4,
    "readinessLevel": "ADVANCED",
    "signals": [
      "34% renewable generation — above average transition progress",
      "Average carbon intensity 218 gCO2/kWh",
      "11 EV charging stations found — growing infrastructure",
      "4 supportive energy regulations in Federal Register"
    ]
  },
  "gridStress": {
    "score": 47,
    "weatherRisk": 20,
    "demandPressure": 20,
    "supplyConstraints": 7,
    "stressLevel": "ADVISORY",
    "signals": [
      "Extreme heat forecast (37°C) — peak cooling demand expected",
      "Grid utilization at 87% — approaching capacity limits"
    ]
  },
  "strandedAssets": {
    "score": 38,
    "fossilLicenses": 7,
    "regulatoryPressure": 9,
    "decarbonizationRate": 42,
    "riskLevel": "MODERATE",
    "signals": [
      "7 fossil fuel licenses at risk of becoming stranded assets",
      "58% fossil fuel generation — high transition stranding exposure"
    ]
  },
  "evInfrastructure": {
    "score": 52,
    "totalChargers": 11,
    "fastChargers": 3,
    "chargerDensity": 11,
    "gapLevel": "UNDERSERVED",
    "signals": [
      "Only 27% fast chargers — slow charging dominates"
    ]
  },
  "allSignals": [
    "34% renewable generation — above average transition progress",
    "Average carbon intensity 218 gCO2/kWh",
    "11 EV charging stations found — growing infrastructure",
    "4 supportive energy regulations in Federal Register",
    "Extreme heat forecast (37°C) — peak cooling demand expected",
    "Grid utilization at 87% — approaching capacity limits",
    "7 fossil fuel licenses at risk of becoming stranded assets",
    "Only 27% fast chargers — slow charging dominates"
  ],
  "opportunities": [
    "EV charging infrastructure gap — UNDERSERVED market for new installations",
    "Grid stability allows accelerated renewable integration"
  ],
  "risks": [
    "7 active fossil licenses — stranded asset write-downs expected"
  ]
}

Output fields

How much does energy transition intelligence cost?

This MCP uses pay-per-event pricing — you pay $0.045 per tool call. Platform compute costs are included. There is no subscription, no monthly fee, and no minimum commitment.

You can set a maximum spending limit per run to control costs. The server returns a clean error message if the per-run budget is reached, rather than continuing to charge.

Apify's free tier includes $5 of monthly platform credits — enough for over 100 tool calls per month at no cost. Compare this to commercial energy data platforms such as Wood Mackenzie or BloombergNEF, which start at $20,000-80,000 per year for comparable market intelligence coverage.

How Energy Transition Intelligence MCP works

Data collection: parallel actor dispatch

When a tool is called, runActorsParallel() dispatches simultaneous requests to the relevant subset of 7 Apify actors using Promise.allSettled. This means a slow or unavailable data source (e.g., the NSTA API under maintenance) does not block the other 5-6 sources from completing. Failed actors return empty arrays, and scoring functions handle missing data gracefully using default fallbacks. Each underlying actor runs with 256MB memory and a 120-second timeout.

The 7 actors and their data roles:

• EIA Energy Data (uY5GBLNv5fxQ2j1Yw) — generation mix, fuel types, demand series, capacity
• Carbon Intensity (DT935ATvR9Fe7Jaqv) — UK grid carbon intensity (live + forecast), intensity, actual, forecast fields
• Open Charge Map (PMfpkCw1ysFSTcx0D) — EV charger records with power_kw, maxPowerKW, level, connection_type
• FRED Economic Data (gz0VOFSLZkFwhqOS8) — DCOILWTICO (WTI crude), DHHNGSP (natural gas), carbon price series
• Weather Forecast (TpfQHy4R1EZT3ZqOp) — temperature, wind_speed, condition per forecast period
• Federal Register (8bZkbWKlXQrDq0ZgK) — rule title, type (proposed/final/notice) from DOE, EPA, FERC
• NSTA Oil & Gas Licenses (hcRLmf3C0wGmaEcnd) — active license records per query

Scoring: four independent models

Transition Readiness Score (0-100): Renewable generation share contributes up to 30 points (scaled: 75% renewable = maximum 30). Carbon intensity contributes up to 25 points (≤100 gCO2/kWh = 25pts, ≤200 = 18pts, ≤300 = 10pts, >300 = 3pts). EV charging station count contributes up to 25 points (2 points per charger, capped at 25). Supportive regulatory environment contributes up to 20 points (4 points per net supportive regulation). Active fossil fuel licenses apply a penalty of up to 15 points (2 points per license).

Grid Stress Predictor (0-100): Weather extremes drive up to 35 points — temperatures above 35°C add 8 points, below -5°C add 8 points, storm conditions add 10 points, wind speeds below 3 m/s add 3 points per period. Supply-demand balance from EIA contributes up to 30 points based on utilization rate thresholds (>90% = 30pts, >80% = 20pts, >70% = 10pts). Peak carbon intensity (peaker plant proxy) contributes up to 20 points (>400 gCO2/kWh = 20pts). Time-of-day (14:00-19:00 UTC peak hours = 10pts) and seasonal demand cycles contribute up to 15 points.

Stranded Asset Risk Index (0-100): Active NSTA license count contributes up to 30 points (3 per license). Fossil fuel generation share contributes up to 25 points. Federal Register regulatory tightening (emissions, carbon, methane, phase-out, ban keywords) contributes up to 25 points. FRED commodity price stress — WTI below $50/barrel (+7pts), gas below $2.50/MMBtu (+5pts), carbon price above $50/ton (+8pts) — contributes up to 20 points.

EV Infrastructure Gap Score (0-100): Charger deficit is inverted — fewer chargers = higher score (≤2 chargers = 35pts deficit, ≤5 = 25pts, ≤10 = 15pts). DC fast charger ratio deficit contributes up to 25 points (<10% fast = 25pts, <20% = 18pts). Grid capacity constraint contributes up to 20 points. EV adoption pressure from FRED vehicle sales data contributes 10-15 points.

Composite scoring and grade assignment

The final composite score weights: readiness score × 0.30 + (100 − grid stress) × 0.20 + (100 − stranded asset risk) × 0.25 + (100 − EV gap) × 0.25. This means a region that is transition-ready (high readiness), grid-stable (low stress), low fossil exposure, and well-served for EVs scores near 100. Letter grades: ≥80 = A, ≥65 = B, ≥50 = C, ≥35 = D, <35 = F.

Outlook is determined by rule: readiness ≥ 60 and stranded risk ≤ 30 → ACCELERATING; readiness ≥ 40 and grid stress ≤ 50 → ON_TRACK; stranded risk ≥ 60 or EV gap ≥ 70 → REGRESSING; else → STALLING.

Transport: Streamable HTTP MCP

The server uses @modelcontextprotocol/sdk v1.11.0 with StreamableHTTPServerTransport — the current MCP specification's preferred transport for server-side deployments. Each POST to /mcp creates a new McpServer instance, connects it to a fresh transport, and handles the request. The server redirects GET requests to the Apify Store page and runs on ACTOR_STANDBY_PORT in Standby mode.

Tips for best results

1. Use generate_energy_transition_brief for first-pass analysis. At the same price per call as individual tools, the brief runs all 7 sources and all 4 scoring models in one call. Use individual tools only when you need to drill deeper into a specific dimension.

2. Supply coordinates for grid stress predictions. The predict_grid_stress tool accepts lat and lon alongside region. Exact coordinates improve weather forecast accuracy, which is the highest-weight component (35 points) in the stress model.

3. Specify asset type for stranded asset assessments. Passing assetType: "natural gas" to evaluate_stranded_asset_risk narrows the NSTA license query and EIA generation data to the relevant fuel type, improving signal-to-noise.

4. Combine with carbon trajectory tracking for ESG reporting. Call track_carbon_trajectory monthly for the same region and store the avgCarbonIntensity time series. This produces the multi-period trend data required for CDP and GRI emissions reporting.

5. Use monitor_energy_regulation with specific topics. Queries like "methane leak detection" or "clean hydrogen production tax credit" return far more relevant Federal Register documents than broad queries like "energy regulation". More relevant documents improve the regulatory support score accuracy.

6. Interpret EV gap scores directionally. A DESERT classification (score ≥ 80) in a region with strong EV adoption pressure signals (from FRED vehicle sales data) indicates a high-priority market for charging network expansion. Cross-reference with the grid stress score to confirm grid capacity headroom.

7. Set a spending limit for large batch assessments. If assessing 50+ regions in an automated pipeline, set a per-run maxTotalChargingUsd in your Apify run input to prevent unexpected spend. At $0.045 per call, 50 full briefs costs $2.25.

Combine with other Apify actors and MCP servers

Limitations

• US and UK geographic bias — EIA data covers the US only. Carbon intensity and NSTA oil/gas license data cover the UK only. EV charging data via Open Charge Map is global. For non-US/UK regions, transition readiness and stranded asset scores will have fewer data inputs, reducing accuracy.
• EIA data latency — US Energy Information Administration datasets are updated monthly to annually, not in real time. Grid stress prediction uses weather and carbon intensity for short-term signals but EIA generation mix data may lag by weeks.
• Carbon intensity is UK-only (live feed) — The carbon intensity actor targets the National Grid ESO API. Non-UK regions will return empty carbon intensity data, and carbon scoring will default to the fallback value, reducing score reliability.
• Regional resolution is approximate — Tool inputs accept free-text region names. The underlying actors interpret these as search queries. Highly specific sub-regional queries (e.g., a specific utility service territory or transmission zone) may return data for a broader area.
• No project-level modeling — All four scoring models operate at regional or national level. The server cannot evaluate a specific wind farm, solar project, or oil field — it assesses the market environment for that category of asset.
• Regulatory signal detection is title-based — The monitor_energy_regulation tool scans Federal Register document titles for keyword matches. Documents with ambiguous or technical titles may be miscategorized as neutral even when substantively relevant.
• NSTA license data is North Sea specific — The NSTA actor covers UK continental shelf licenses. Non-UK fossil fuel license data is not available through this server. Stranded asset risk scoring for non-UK regions relies on EIA fuel mix and FRED pricing signals only.
• Spending limit stops mid-pipeline — If a spending cap is reached during a generate_energy_transition_brief call (which charges a single event before running), the tool returns a budget error before any data is fetched. There is no partial result.

Integrations

• Claude Desktop — add the MCP URL to claude_desktop_config.json and use natural language to request transition assessments, grid stress checks, and regulatory monitoring directly in conversation
• Cursor — configure as an MCP server in Cursor settings to bring energy transition tools into your development workflow for energy sector applications
• Apify API — invoke the standby actor endpoint directly from any HTTP client for programmatic integration with investment platforms, ESG tools, or energy dashboards
• Zapier — trigger weekly energy transition assessments on a schedule and push results to Google Sheets, Slack, or HubSpot when grid stress levels exceed a threshold
• Make — build automated reporting pipelines that run generate_energy_transition_brief across a portfolio of regions and format results into structured reports
• Webhooks — receive push notifications when high-priority assessments complete, enabling real-time grid stress alerts for operations teams
• LangChain / LlamaIndex — integrate energy transition tools into multi-step AI agent pipelines alongside other data sources for comprehensive investment research automation

Troubleshooting

Empty or very low scores despite a valid region name — This usually means the underlying data sources returned no results for the query. Regions outside the US and UK will have limited EIA and carbon intensity coverage, so readiness and grid stress scores may reflect only the EV and regulatory sub-components. Try a broader region name (e.g., "United States" rather than a specific state code) or check that the region spelling matches what the underlying APIs expect.

predict_grid_stress returning NORMAL when you expect higher stress — The weather sub-component (maximum 35 points) depends on forecast temperature and wind data matching the region query. If the weather actor returns no results, the weather score defaults to zero. Pass explicit lat and lon coordinates alongside the region parameter to ensure the weather actor resolves the correct location.

Spending limit error on generate_energy_transition_brief — The brief tool charges a single generate_energy_transition_brief event ($0.045) at the start of the call, before any data is fetched. If your per-run spending limit is below $0.045, the tool will immediately return the limit-reached error. Ensure your run spending limit is set to at least $0.10 for the brief tool.

Tool timeout on large region queries — Each underlying actor runs with a 120-second timeout. For very broad queries (e.g., "global" or "Europe"), some actors may time out before returning data. Use more specific regional names and allow 60-90 seconds for generate_energy_transition_brief to complete.

Stranded asset risk showing MINIMAL for a known fossil-heavy region — The stranded asset model requires NSTA license data (UK only) for the license count sub-component. For non-UK fossil regions, only the EIA fuel mix and FRED price signals contribute to the score. The maximum achievable score for non-UK regions is approximately 45 (out of 100), capped by the absent license component.

Responsible use

• This server accesses only publicly available government and open-data sources: US EIA, UK National Grid ESO, Open Charge Map, Federal Reserve, US Federal Register, and UK NSTA.
• Energy transition scores and grades are analytical outputs derived from available data. They should supplement, not replace, professional investment, engineering, or regulatory advice.
• Do not use automated regulatory monitoring outputs as legal compliance guidance without verification by qualified counsel.
• For guidance on web scraping legality, see Apify's guide.

FAQ

How accurate is the energy transition readiness score? The score is a quantitative model based on publicly available data with documented point allocations. It is most reliable for US states (full EIA + Federal Register coverage) and UK regions (carbon intensity + NSTA data). For other geographies, accuracy is reduced because EIA and carbon intensity data will not be present, and only the EV and partial regulatory components will contribute to the score. Treat scores as relative rankings for comparison rather than absolute ground truth.

What geographies does energy transition intelligence cover? US data is provided via EIA and Federal Register — covering all 50 states and energy regions. UK-specific data comes from Carbon Intensity (National Grid ESO) and NSTA oil/gas licenses. EV charging data via Open Charge Map is global. Weather and FRED economic data have worldwide coverage. The server works best for US and UK regions where all 7 data sources contribute fully.

How does energy transition readiness scoring differ from commercial energy data platforms? Commercial platforms like Wood Mackenzie and BloombergNEF offer proprietary analyst-built models, historical datasets, and bespoke advisory. This MCP provides a structured, automated scoring model built on public data sources at $0.045 per query with no subscription commitment. It is best suited for screening and monitoring workflows rather than replacing deep analyst research.

Can I use energy transition intelligence for investment decisions? Yes, as an analytical input. The scores and signals are designed to surface transition risk and opportunity in a structured format that can inform — but should not solely drive — investment decisions. Pair the output with primary research, financial modeling, and professional advisory for material investment decisions.

How real-time is the grid stress prediction? UK carbon intensity data via the National Grid ESO API is near real-time (updates every 30 minutes). Weather forecast data provides a 48-72 hour lookahead. US EIA supply-demand data has varying update frequencies (some series update weekly, most monthly). The grid stress predictor is most accurate for UK regions and for short-term weather-driven demand spikes anywhere.

How does the stranded asset risk model work? The model cross-references four signal categories: active UK NSTA oil and gas license count (up to 30 points), fossil fuel generation share from EIA data (up to 25 points), regulatory tightening signals from Federal Register titles (up to 25 points), and commodity price stress from FRED crude oil and natural gas prices (up to 20 points). Higher scores indicate greater exposure to asset stranding from the energy transition.

Can I schedule energy transition monitoring to run automatically? Yes. Use Apify's scheduling feature to run the server on any interval — daily, weekly, or custom. You can also use webhooks to push results to Slack, Google Sheets, or your own systems when assessments complete. See the Integrations section for configuration options.

Is it legal to use the data this MCP accesses? All data sources are public government databases and open-data registries: the US Energy Information Administration, US Federal Reserve (FRED), US Federal Register, National Grid ESO (UK), Open Charge Map, and UK NSTA. Accessing and analyzing this data is legal. See Apify's guide on web scraping legality for broader context.

How is the transition outlook (ACCELERATING / ON_TRACK / STALLING / REGRESSING) determined? Outlook is determined by a rule-based classifier applied after all four scoring models run: if readiness score is ≥ 60 and stranded asset risk is ≤ 30, the outlook is ACCELERATING. If readiness is ≥ 40 and grid stress is ≤ 50, it is ON_TRACK. If stranded asset risk is ≥ 60 or EV gap is ≥ 70, it is REGRESSING. Otherwise it is STALLING.

Can I combine this with other MCP servers in one AI agent session? Yes. Any MCP-compatible client (Claude Desktop, Cursor, Windsurf, Cline) supports multiple MCP servers simultaneously. You can combine energy transition intelligence with a data center siting MCP, a company research MCP, or any other server in the same agent session. The AI client will select the appropriate tool from the appropriate server based on your query.

How many tool calls does a typical energy investment analysis require? A typical regional screening workflow uses 1 call to generate_energy_transition_brief for each region being evaluated ($0.045 per region), plus 1-2 follow-up calls to evaluate_stranded_asset_risk or analyze_ev_infrastructure_gaps for regions flagging moderate or high risk. Screening 10 regions costs approximately $0.45-$0.90 total.

What happens if one of the 7 underlying data sources is unavailable? The server uses Promise.allSettled for parallel dispatch. If one actor times out or returns an error, the other actors complete normally. The scoring functions treat missing data as empty arrays and apply only the sub-components with available data. The response still returns with a score, though the affected sub-components will reflect the absence of that data source.

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 energy data integrations, additional geographic coverage, or enterprise deployments, reach out through the Apify platform.