# exascale.build — AI Connector exascale.build publishes 8 MCP tools to Claude. Marketplace availability, tool surface, verification tier, and what Node8 measured against the live endpoint. Source: https://node8.ai/ai-connectors/data-analytics/exascale-build/ --- [AI Connectors](https://node8.ai/ai-connectors/) · [Data & Analytics](https://node8.ai/ai-connectors/data-analytics/) # exascale.build Source-cited US power generation and capacity data over MCP Listed in Claude · 8 published tools · Community-listed [Claude connector docs](https://exascale.build/docs) [exascale.build](https://exascale.build) Overview ## What exascale.build does exascale.build publishes US power system data drawn from EIA filings: operating, planned and retired generation capacity from EIA-860M, net generation from EIA-923, and capacity factor. Takezo's stated design point is provenance. Every value returns with its source and an as-of date, and any figure resolves to the raw source cell with a matching SHA-256 hash. Each dataset is reachable two ways, a describe call that states the shape and scope of a capability and a query call that runs against it. The listing says tools declare what they will not answer, so an agent refuses out-of-scope questions instead of guessing. Access is over MCP or REST without credentials, and the connector is community-listed. ### Who it is for Energy analysts who need US generation figures with a traceable source for every number. ### Tool surface Fourteen tools answered against eight claimed in the listing. They pair up, a describe\_ call and a query\_ call for each dataset across power capacity, generation, asset ownership, fuel cost and plant costs, with list\_capabilities\_v1 and get\_source\_evidence\_v1 covering provenance. Availability ## Where exascale.build is listed exascale.build is listed in the Claude connectors directory only. Takezo has no app under the same domain in the ChatGPT directory; 392 of the 3,150 products here are on both marketplaces, and this is not one of them. The MCP server behind a Claude connector is usually the same server a ChatGPT app would need, so the absence is a distribution decision rather than a technical one. Claude listing ## In the Claude connectors directory exascale.build publishes 8 tools to Claude. That is a mid-sized surface: 37.7% of the 1,253 Claude-listed connectors expose fewer. The median Claude-listed connector filed under Data & Analytics publishes 12, so this one sits 4 tools below its bucket's median, 123rd of 198. It falls in the 7-10 tools band, which holds 14.6% of the Claude directory. ### Measured against the live endpoint A direct call to the endpoint returned 66 tools, 58 more than the 8 the listing publishes. Probed 2026-08-07. #### Tools the server actually returns - `list_capabilities_v1` - `get_source_evidence_v1` - `describe_capability_v1` - `query_capability_v1` - `describe_power_capacity_v1` - `query_power_capacity_v1` - `describe_power_generation_v1` - `query_power_generation_v1` - `describe_power_asset_ownership_v1` - `query_power_asset_ownership_v1` - `describe_power_fuel_cost_v1` - `query_power_fuel_cost_v1` - `describe_power_plant_costs_v1` - `query_power_plant_costs_v1` - `describe_natural_gas_prices_v1` - `query_natural_gas_prices_v1` - `describe_power_demand_v1` - `query_power_demand_v1` - `describe_power_demand_rollup_v1` - `query_power_demand_rollup_v1` - `describe_power_retail_sales_v1` - `query_power_retail_sales_v1` - `describe_power_interconnection_queue_v1` - `query_power_interconnection_queue_v1` - `describe_power_interconnection_queue_pjm_v1` - `query_power_interconnection_queue_pjm_v1` - `describe_power_interconnection_queue_pjm_cycle_v1` - `query_power_interconnection_queue_pjm_cycle_v1` - `describe_power_interconnection_queue_caiso_v1` - `query_power_interconnection_queue_caiso_v1` - `describe_power_interconnection_queue_nyiso_v1` - `query_power_interconnection_queue_nyiso_v1` - `describe_power_interconnection_queue_isone_v1` - `query_power_interconnection_queue_isone_v1` - `describe_power_interconnection_queue_ercot_v1` - `query_power_interconnection_queue_ercot_v1` - `describe_power_interconnection_queue_spp_v1` - `query_power_interconnection_queue_spp_v1` - `describe_power_price_ercot_v1` - `query_power_price_ercot_v1` - `describe_power_capacity_accreditation_pjm_v1` - `query_power_capacity_accreditation_pjm_v1` - `describe_power_capacity_market_pjm_v1` - `query_power_capacity_market_pjm_v1` - `describe_power_capacity_accreditation_miso_v1` - `query_power_capacity_accreditation_miso_v1` - `describe_power_capacity_market_miso_v1` - `query_power_capacity_market_miso_v1` - `describe_ai_infrastructure_construction_v1` - `query_ai_infrastructure_construction_v1` - `describe_ai_infrastructure_employment_v1` - `query_ai_infrastructure_employment_v1` - `describe_ai_infrastructure_trade_v1` - `query_ai_infrastructure_trade_v1` - `describe_ai_infrastructure_equipment_trade_v1` - `query_ai_infrastructure_equipment_trade_v1` - `describe_ai_infrastructure_production_v1` - `query_ai_infrastructure_production_v1` - `describe_robotics_trade_v1` - `query_robotics_trade_v1` - `describe_robotics_adoption_v1` - `query_robotics_adoption_v1` - `describe_space_satellite_filings_v1` - `query_space_satellite_filings_v1` - `describe_capacity_factor_v1` - `query_capacity_factor_v1` exascale.build publishes a remote MCP endpoint. Claude connects to it over HTTP; there is nothing to install locally. Every connector in the Claude directory is remote, all 1,253 of them, so transport is not a differentiator there. Publisher Takezo Verification Community-listed (61.5% of the Claude directory) Filed under Data & Analytics Endpoint `https://api.exascale.build/mcp` Documentation [Publisher setup docs](https://exascale.build/docs) Published tools 8 · 7-10 tools band Depth rank in Data & Analytics 123 of 198 Snapshot August 2026 exascale.build is community-listed in the Claude directory, the tier 770 of 1,253 connectors sit in (61.5%). It is the default for a self-published server, and says nothing either way about quality. In the publisher's words ## How Takezo describes it > Agent-first, source-cited data layer for the US power system. Query operating, planned, and retired generation capacity (EIA-860M), net generation (EIA-923), and capacity factor — over MCP or REST. Every value returns with its source and as-of date, and any number resolves to its raw source cell with a matching SHA-256, so an agent's answer is verifiable in one call. Tools declare what they won't answer, so the agent refuses out-of-scope questions instead of guessing. Free and open today; industrial and logistics rolling out. Quoted from the connector's own Claude directory listing as captured in August 2026. Node8 did not write it and does not vouch for it. Nearby ## Other Data & Analytics connectors ### [Evarist](https://node8.ai/ai-connectors/data-analytics/evarist/) Web analytics questions answered with session-level evidence Claude ### [Atomscale](https://node8.ai/ai-connectors/data-analytics/atomscale/) Materials characterisation data, notebooks, and instrument streams Claude ### [Companion.energy](https://node8.ai/ai-connectors/data-analytics/companion-energy/) Read-only energy analytics for commercial and industrial sites Claude ### [DataHub](https://node8.ai/ai-connectors/data-analytics/datahub/) Enterprise data context: search, lineage, ownership and governance Claude ### [dbt](https://node8.ai/ai-connectors/data-analytics/dbt/) Browse, query and run dbt projects and the semantic layer Claude ### [Deepnote](https://node8.ai/ai-connectors/data-analytics/deepnote/) Notebook workspace access for analysis and execution ChatGPT [All 260 Data & Analytics connectors](https://node8.ai/ai-connectors/data-analytics/) This is an independent catalogue entry compiled by Node8 from exascale.build's public marketplace listing as it stood in August 2026. Listing facts come from the marketplaces; the comparisons against the rest of the directory and any live-endpoint measurements are Node8's. Node8 is not affiliated with Takezo, and inclusion here is not an endorsement. ## Want your company reachable inside ChatGPT and Claude? Node8 builds MCP servers end to end: deciding which tools are worth exposing, the authentication and permission model, the review submissions, and the onboarding that gets them used. One server serves ChatGPT, Claude, and Microsoft Copilot. [See how it works](https://node8.ai/mcp) Book a strategy session