---

Tools

Seven tools covering the two-phase EIA workflow — find the right dataset route, pull the data, and query spilled results via SQL:

Tool	Description
eia_browse_routes	Lists child routes under a given path in the EIA dataset taxonomy. Start at root to see top-level categories, then drill into subcategories and leaf routes.
eia_describe_route	Returns metadata for a leaf route: available facets with valid values, data column names, frequency options, units, and date range. Call before eia_query_route to understand filter options. Facet values come back capped, with facet and values_offset to page one facet.
eia_search_routes	Fuzzy text search across route names, descriptions, category labels, STEO series names, and facet values. Resolves natural-language queries like "electricity retail sales by state" or a fuel type like "wind" to matching route paths.
eia_query_route	Fetches data from a leaf route with optional facet filters, date range, frequency, and column selection. Pages past the inline preview to stage large result sets as a DataCanvas table for SQL analysis.
eia_dataframe_describe	Lists active DataCanvas dataframes created by prior eia_query_route calls. Shows table name, column names and types, row count, expiry, and the query that produced it. A handle that is not staged comes back as a miss alongside the handles that are.
eia_dataframe_query	Runs a read-only SQL SELECT across DataCanvas dataframes, referenced by their df_<id> table names.
eia_dataframe_drop	Drops a DataCanvas dataframe, freeing its memory. Only exposed when EIA_DATAFRAME_DROP_ENABLED=true.

eia_browse_routes

Walk the EIA dataset taxonomy from root to leaf.

• Root call returns 14 top-level categories: electricity, petroleum, natural-gas, coal, international, total-energy, steo, aeo, ieo, seds, crude-oil-imports, nuclear-outages, densified-biomass, co2-emissions
• Intermediate paths return subcategories; leaf routes are flagged so callers know when to switch to eia_describe_route
• STEO (Short-Term Energy Outlook) is a flat leaf with 1,469 named series — no sub-routes

---

eia_describe_route

Full schema for a leaf route. Required before constructing facet filters.

• Returns facets with valid values (fetched via per-facet API calls and cached in-process)
• Returns data column names, units, frequency options, and date range
• Each facet returns at most EIA_FACET_VALUE_CAP values, alongside value_count and values_truncated. Pass facet with values_offset to page one facet past the cap — the cap shapes this tool's response only, and the in-process cache keeps every value
• eia_search_routes and eia_browse_routes resolve the route path; this tool provides the filter vocabulary

---

eia_search_routes

Fuzzy search across the in-memory route index.

• Indexes route names, descriptions, and category labels — plus STEO's 1,469 series names and facet values
• Resolves natural language ("natural gas spot prices", "ethanol net imports") to queryable route paths, and a fuel-type or sector term ("wind", "anthracite coal") to the route that exposes it, with a filter_hint to pass straight to eia_query_route
• A multi-term query is also matched term by term, so combining a commodity, a metric, and a sector ("electricity price residential", "coal generation industrial sector") reaches the route carrying that data even when no single entry reads like the whole phrase. Each result keeps the better of its whole-phrase and per-term score; a single-term query takes the phrase path alone
• score runs 0 (exact) to 1 (no match), lower is better; above 0.72 the match is unreliable and the query is worth narrowing. bun run eval:search scores a labelled query battery against a live corpus, which is where that number comes from
• The first call waits for the whole corpus to warm — 24–30 s measured against the live API from cold, and never more than 45 s, so a degraded upstream cannot hold the call past a client's request timeout. Every later search is served from the in-process Fuse.js index in tens of milliseconds, with no upstream cost
• indexComplete reports whether the answer was ranked against the whole corpus; when it is false, indexGaps names the routes and index passes that are missing, so a short result set is never mistaken for a settled one

---

eia_query_route

Pull data from a leaf route.

• Facet filters keyed by facet ID (e.g. { "stateid": "TX", "sectorid": ["RES", "COM"] })
• Date range and frequency selection; valid values discoverable via eia_describe_route
• Pagination via offset/length (max 5,000 rows per page); total row count in response
• All numeric values arrive as strings from the EIA API — units appear as inline {col}-units fields per row
• DataCanvas spillover when the result set exceeds length: further pages are fetched and the accumulated rows are staged as a dataset (df_<id>) for SQL, bounded by EIA_CANVAS_MAX_ROWS. The response note names how many rows actually reached the table.

Features

Built on @cyanheads/mcp-ts-core:

• Declarative tool definitions — single file per tool, framework handles registration and validation
• Unified error handling — handlers throw, framework catches, classifies, and formats
• Pluggable auth: none, jwt, oauth
• Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1
• Structured logging with optional OpenTelemetry tracing
• STDIO and Streamable HTTP transports

EIA-specific:

• Full coverage of EIA API v2 — all 14 top-level dataset categories
• In-process route tree cache with Fuse.js fuzzy index — built once on first use at a paced request rate, no repeated upstream calls
• Facet values are searchable: a bounded pass indexes the fuel-type, sector, and technology vocabulary named in the route tree, and every described route folds its own values in at no upstream cost
• Warm gaps are tracked, not swallowed: a route whose metadata could not be fetched is held as an incomplete stub rather than passed off as a queryable leaf, reported through eia_search_routes, and re-fetched by the next eia_browse_routes call that reaches it
• Per-route facet cache via Promise.all fan-out — valid filter values available without re-fetching
• STEO series names (1,469 entries) indexed for natural-language discovery
• DataCanvas (DuckDB) opt-in for tabular spillover — graceful degradation when unavailable

Getting started

Get a free API key at api.eia.gov, then add the following to your MCP client configuration file.

{
  "mcpServers": {
    "eia-energy-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/eia-energy-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info",
        "EIA_API_KEY": "your-api-key"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "eia-energy-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/eia-energy-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info",
        "EIA_API_KEY": "your-api-key"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "eia-energy-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "-e", "EIA_API_KEY=your-api-key",
        "ghcr.io/cyanheads/eia-energy-mcp-server:latest"
      ]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 EIA_API_KEY=your-key bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

• Bun v1.3.0 or higher (or Node.js v24+).
• A free EIA API key from api.eia.gov. The DEMO_KEY hits rate limits quickly; a real key is required for sustained use.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/eia-energy-mcp-server.git

2. Navigate into the directory:

cd eia-energy-mcp-server

3. Install dependencies:

bun install

4. Configure environment:

cp .env.example .env
# edit .env and set required vars (at minimum, EIA_API_KEY)

Configuration

All configuration is validated at startup via Zod schemas in src/config/server-config.ts. Key environment variables:

Variable	Description	Default
EIA_API_KEY	Required. Free API key from api.eia.gov — appended as api_key on every request.	—
EIA_BASE_URL	EIA API base URL.	https://api.eia.gov/v2
EIA_DATASET_TTL_SECONDS	Sliding per-dataframe TTL in seconds. The window is extended every time an eia_dataframe_query statement references the dataframe, so a dataframe stays alive through a long analysis and lapses only once it goes unused for the full interval. Listing it with eia_dataframe_describe is not use and does not extend it.	86400 (24 h)
EIA_DATAFRAME_DROP_ENABLED	Set to true to expose eia_dataframe_drop. Off by default to avoid accidental canvas cleanup.	false
EIA_CANVAS_MAX_ROWS	Cumulative row ceiling for eia_query_route canvas staging — five requests at EIA's 5,000-row-per-request ceiling, adding ~8.5 s to a call when it binds. Lower it for snappier exploration, raise it for wider staged analyses.	25000
EIA_FACET_VALUE_CAP	Facet values eia_describe_route returns per facet before truncating. Bounds the response on high-cardinality facets — STEO's seriesId alone has 1,469 values. Page past it with the tool's facet and values_offset inputs.	50
CANVAS_PROVIDER_TYPE	Set to duckdb to enable DataCanvas spillover for large result sets (Node only).	—
MCP_TRANSPORT_TYPE	Transport: stdio or http.	stdio
MCP_HTTP_PORT	HTTP server port.	3010
MCP_HTTP_ENDPOINT_PATH	HTTP endpoint path.	/mcp
MCP_PUBLIC_URL	Public origin override for TLS-terminating reverse-proxy deployments.	—
MCP_AUTH_MODE	Auth mode: none, jwt, or oauth.	none
MCP_LOG_LEVEL	Log level (RFC 5424).	info
LOGS_DIR	Directory for log files (Node.js only).	<project-root>/logs
STORAGE_PROVIDER_TYPE	Storage backend: in-memory, filesystem, supabase, cloudflare-kv/r2/d1.	in-memory
OTEL_ENABLED	Enable OpenTelemetry instrumentation.	false

Running the server

Local development

• Build and run:

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:stdio
  # or
  bun run start:http
  

• Run checks and tests:

  bun run devcheck   # Lint, format, typecheck, security
  bun run test       # Vitest test suite
  bun run lint:mcp   # Validate MCP definitions against spec
  

Project structure

Directory	Purpose
src/index.ts	createApp() entry point — registers tools and inits services.
src/config	Server-specific environment variable parsing and validation with Zod.
src/mcp-server/tools	Tool definitions (*.tool.ts) — browse, describe, search, query, and three DataCanvas dataframe tools.
src/services/eia	EIA API v2 service — route tree cache, Fuse.js index, facet fan-out, HTTP client.
src/services/canvas-bridge	DataCanvas bridge — registers EIA query results as DuckDB dataframes, routes SQL queries.
tests/	Unit and integration tests mirroring src/.
docs/	Design documents (design.md, idea.md).

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic
• Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage
• Always call eia_describe_route before eia_query_route — facet values require a separate API fan-out and are not embedded in route metadata
• Wrap EIA responses: validate raw → normalize to domain type → return output schema; data values are strings — never coerce silently

Contributing

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.