mcp-openei-urdbSAFE
OpenEI Utility Rate Database (URDB) MCP
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
NREL's Utility Rate Database (URDB) — US electricity tariffs: residential, commercial and industrial rate schedules with their energy charges by tier and time-of-use period, demand charges, fixed monthly charges, net-metering treatment and effective dates, keyed to the utility's EIA id.
Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.
Tools
urdb_search_rates(address? | latitude+longitude | utility | eia_id, sector?, detail?, approved_only?, limit?, offset?, _apiKey?)—
search tariffs.
urdb_rate_detail(label, _apiKey?)— the full structure of one tariff,
including the 12x24 month-by-hour period schedules a bill calculation needs.
urdb_utilities_for_location(address? | latitude+longitude | filter, _apiKey?)—
which utilities serve a location, with tariff counts and how many are current.
Auth
The OpenEI API takes an api_key. NREL's public `DEMO_KEY` is accepted and returns real rows (verified 2026-09-17), so this pack works with no configuration at a low rate limit — it is not a gated pack.
Callers who exceed the DEMOKEY limit pass their own free NREL key as `apiKey`. Free key:
A platform key would be read from the injected _platformKey argument (PLATFORM_NREL_KEY). It is not declared as platformKeyEnv in the pack manifest and must not be until the secret actually exists: the gateway is at Cloudflare's 250-text-binding cap, and declaring the flag without the secret would route rate questions to a tool that could only refuse.
Data sources
- — rate search and detail.
- — utility name directory.
developer.nrel.gov/api/utility_rates/v3.json was not reachable from our egress on 2026-09-17 (connection failure, not an HTTP error) and is not used.
Traps
Every one of these returns HTTP 200.
5bfe5d2c4fb2OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-openei-urdb -- npx -y @pipeworx/[email protected]
{
"mcpServers": {
"mcp-openei-urdb": {
"command": "npx",
"args": [
"-y",
"@pipeworx/[email protected]"
]
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
urdb_search_rates | read | AUTHORITATIVE for US electricity tariffs: search the NREL Utility Rate Database for electricity rate schedules by location, utility name or EIA utility id, and get each tariff\ |
urdb_utilities_for_location | read | Find which electric utilities serve a US location, with how many tariffs each has in the NREL rate database, which sectors they cover, and how many of those tariffs are still current. Answers |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, tsx, typescript, @cloudflare/workers-types
Gates applied: no_behavioural_pass.
5bfe5d2c4fb2full audit observations/trust-audit/mcp-server/pipeworx-io__mcp-openei-urdb.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 5bfe5d2c4fb2 | SAFE | B | 89 | first audit |
Questions
What is the mcp-openei-urdb MCP server?
OpenEI Utility Rate Database (URDB) MCP
What tools does mcp-openei-urdb expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is mcp-openei-urdb safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does mcp-openei-urdb need?
No credential environment variables were found in its source, so it appears to need none.
How does mcp-openei-urdb run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @pipeworx/mcp-openei-urdb at 0.1.1.
How current is this page?
The grade is for one exact copy of the source (5bfe5d2c4fb2), read on 2026-10-11. The repository is watched and re-audited when it changes.