kardashev-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KARDASHEV_BASE_URL | No | Override API base (local data plane) | https://data.kardashevlabs.org |
| KARDASHEV_TIMEOUT_MS | No | Per-request timeout | 30000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_isosA | List US ISOs/RTOs covered by Kardashev Labs and their live ingest status. Call this first to discover valid iso codes for other tools. |
| get_fuel_mixA | Generation by fuel type (MW) for a US ISO. Use latest=true for the newest snapshot; otherwise returns recent history (row-capped). |
| get_carbonA | Grid carbon intensity in lbs CO₂/MWh. Omit iso with latest=true for all balancing authorities; pass iso for one region. Prefer this over raw fuel-mix when the question is about emissions intensity. |
| get_lmpA | Locational marginal prices (LMP) for a US ISO. market=RT (real-time) or DA (day-ahead). Optionally filter by node_id. This is settled/observed prices — for Kardashev's forward RT−DA spread forecast use get_spread_forecast instead. |
| get_loadC | Actual electricity demand (MW) for a US ISO or zone. |
| get_load_forecastA | Near-term ISO load forecast (MW). Not the ERCOT RT−DA price-spread forecast — use get_spread_forecast for that. |
| get_curtailmentA | Solar and wind curtailment (MWh) by ISO. Strongest coverage for CAISO, ERCOT, SPP. |
| get_queueA | Search generator interconnection queue projects across US ISOs/RTOs — projects waiting to connect to the grid. Filter by iso, fuel_type, status, state, or min_mw. |
| get_large_loadA | ERCOT large-load interconnection queue snapshot and summary (data centers, crypto, industrial). ERCOT-only. Use summary=true for aggregates; default returns latest rows. |
| get_spread_forecastA | Kardashev Labs live ERCOT day-ahead RT−DA price spread forecast (p10/p50/p90), issued before delivery and never revised. spread = RT − DA. Optional node_id filter (e.g. HB_BUSAVG, HB_NORTH). For scored historical performance use get_forecast_track_record. |
| get_forecast_track_recordA | Public scored track record for Kardashev Labs ERCOT RT−DA spread models (MAE/RMSE/coverage/DART PnL). Use this to evaluate forecast quality; use get_spread_forecast for the live forward issuance. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Each tool targets a distinct data type or service. Potential overlaps like get_lmp vs get_spread_forecast or get_queue vs get_large_load are clearly differentiated by descriptions, leaving little ambiguity.
The vast majority follow a get_<noun> pattern with clear, descriptive nouns. One exception is list_isos, which uses 'list' instead of 'get', but this is a minor deviation and the set remains highly consistent.
With 11 tools, the server covers a broad energy-domain surface without excessive fragmentation. Each tool appears necessary for a distinct type of grid data, fitting well within the typical well-scoped range.
The tool set provides a comprehensive view of ISO load, generation, pricing, emissions, curtailment, and interconnection queues, plus specialized forecasts and track records. Minor gaps like a dedicated wind/solar forecast or historical load export exist, but core workflows are fully supported.