ratebook-mcp
MCP server exposing the Ratebook tariff database and rate engine to apps, devices, and agents.
It answers "what will this kWh cost me, and when should I charge?" over the loaded corpus
(data/ratebook.duckdb) and the deterministic ratebook engine.
mcp-name: io.github.cbetz/ratebook
Tools
| Tool | What it does |
|---|---|
lookup_tariff(query, sector, active_only, limit) |
Find tariffs by utility name, EIA id, or label — freshest first, with provenance (source URL, effective date, last update) and whether the engine can fully price each. |
estimate_bill(label, start_date, days, total_kwh | hourly_kwh) |
Price one tariff over a billing window. total_kwh suffices for flat/tiered/seasonal plans; time-of-use plans need hourly_kwh (length days*24). Returns the full result, with a typed refusal when it can't be priced. |
compare_plans(labels, start_date, days, total_kwh | hourly_kwh) |
Price several tariffs over the same usage and rank cheapest-first; unpriceable plans are listed with their refusal. |
best_charge_window(label, start_date, days, charge_hours, kwh_to_add) |
The cheapest contiguous block to add load (e.g. EV charging), using the tariff's time-of-use marginal price signal. |
Every Decimal is returned as a string (the engine's canonical wire form), so responses are directly JSON-serializable. "Unknown" is a first-class answer: an unpriceable plan returns a typed refusal, never a wrong number.
Run
uv run ratebook-data urdb # build data/ratebook.duckdb first (once)
uv run ratebook-mcp # stdio MCP server
Set RATEBOOK_DB to point at a corpus elsewhere. Register with an MCP client (e.g. Claude
Desktop / Code) as a stdio server running ratebook-mcp from a directory containing the DB:
{
"mcpServers": {
"ratebook": { "command": "uv", "args": ["run", "ratebook-mcp"], "cwd": "/path/to/ratebook" }
}
}
The logic lives in ratebook_mcp.service (unit-testable without a running server); server.py
is the thin FastMCP binding.
Metadata
Release files for ratebook-mcp 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ratebook_mcp-0.1.0.tar.gz | 10.1 kB | Without provenance | Details for ratebook_mcp-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ratebook_mcp-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for ratebook_mcp-0.1.0-py3-none-any.whl |
Total release size: 21.3 kB
Release files / ratebook_mcp-0.1.0.tar.gz
| Download URL | ratebook_mcp-0.1.0.tar.gz |
|---|---|
| Size | 10.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
36f29d1339ec0d8219203fdfe829ea2bf19996ee2c4fa0a6fbe9cd2e70bc9a96
|
|
BLAKE2b-256 checksum How to use checksums |
72d6202fd5f7342317b65b75ad9062c02501b7c4db4921db0bec1be7efafd176
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.4
|
Release files / ratebook_mcp-0.1.0-py3-none-any.whl
| Download URL | ratebook_mcp-0.1.0-py3-none-any.whl |
|---|---|
| Size | 11.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
53229d512bf274b2f69032fdb5e0aac2bf23ad1bb1960208980f29a799dc8fab
|
|
BLAKE2b-256 checksum How to use checksums |
2f874a817b5dad15bd3f53ee1a579dc99f502c6830eb3b97b9eb0bc71630802f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.4
|
Security for ratebook-mcp 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.