How do I use sens-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@sens-mcp Show me current electricity prices for the G11 tariff in Warsaw" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

de en es ja ko ru zh

sens-mcp

by SofiaFlux

Overview Schema Source Related Servers Discussions Admin

Python

Remote

sens-mcp

An MCP (Model Context Protocol) server and developer starter kit for the SENS Energy Data API — the Polish electricity market data API (distribution operators, tariffs, and composite price calculations).

It solves the "cold start" problem for LLMs and AI agents (Claude Desktop, Cursor, LangChain, n8n, ...) talking to the API: the Polish energy market has its own vocabulary (OSD vs. sprzedawca, tariff groups G11/G12/G12w/...) that models don't know out of the box, and raw REST responses are too large and too easy to miscalculate against by hand.

sens-mcp provides:

Zero-shot discoverability — an MCP resource (sens://market/cheat-sheet) and discovery tools (resolve_operator, search_tariffs) that teach the model the market vocabulary in under ~400 tokens.
Actionable self-correction — tool errors return structured JSON with suggestions (did you mean G12w?) instead of raw HTTP failures, so an agent in a ReAct loop can repair its own next call.
Single source of truth calculations — all price/volume math happens on the SENS backend; the toolkit never re-derives totals client-side.
Non-blocking startup — the server boots instantly with an embedded fallback market schema; live tariff metadata refreshes in the background.

Quickstart

Run via `uvx` (recommended, no install step)

export SENS_API_KEY=sens_live_your_key_here
uvx sens-mcp

Or install with pip

pip install sens-mcp
export SENS_API_KEY=sens_live_your_key_here
python -m sens_mcp

Environment variables

Variable	Required	Default	Description
`SENS_API_KEY`	Yes	—	Your SENS API key. Sent as the `X-API-KEY` header.
`SENS_BASE_URL`	No	`https://api.getsens.energy`	Override for staging/self-hosted deployments.

Related MCP server: US ISO Grid MCP

Using it with an AI agent

Claude Desktop

Add to claude_desktop_config.json (see configs/claude_desktop_config.json):

{
  "mcpServers": {
    "sens-energy": {
      "command": "uvx",
      "args": ["sens-mcp"],
      "env": {
        "SENS_API_KEY": "sens_live_your_key_here"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json (see configs/cursor_mcp.json) — same shape as above.

Tools exposed

Tool	Purpose
`resolve_operator(query, region=None)`	Fuzzy-resolve a city or company name (typo-tolerant) to the exact `osd`/`sprzedawca` strings the API expects.
`search_tariffs(customer_type, zone_preference=None, operator=None)`	Discover valid tariff codes for a customer profile (home / small business / industry).
`get_prices(osd, taryfa, ...)`	Fetch composite electricity prices and rate breakdown; pass `annual_kwh` for exact volume-weighted totals.
`get_tariff_components(tariff_id)`	Inspect a tariff's URE-approved fixed/variable rate components.

Resource: sens://market/cheat-sheet — a Markdown cheat sheet of Polish electricity market vocabulary (OSDs, tariff groups, price component structure).

Developer examples (no MCP required)

Standalone snippets that hit the SENS REST API directly:

examples/python/get_prices.py
examples/python/list_tariffs.py
examples/python/async_stream.py — delta sync via since
examples/typescript/get_prices.ts
examples/curl/api_requests.sh

API reference (essentials)

Base URL: https://api.getsens.energy
Auth: X-API-KEY: <your key> header (not Bearer, not a query param).
GET /api/v1/prices — osd, sprzedawca, taryfa, market, date, annual_kwh, region, since, page, size (max 1000).
GET /api/v1/tariffs — since/If-Modified-Since for delta queries, page, size.
GET /api/v1/tariffs/components?tariff_id=... — component breakdown for a single tariff, also supports since.

Full Swagger/OpenAPI docs: https://api.getsens.energy/api/docs. Full developer documentation (quickstart, MCP integration guide, market vocabulary): docs.getsens.energy.

Development

python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
pytest

Tests mock all HTTP calls with respx — nothing in the default test suite hits the live API.

Live integration suite (opt-in)

tests/test_live_integration.py runs the real server as a subprocess over the real MCP stdio protocol against the real production SENS API, and checks byte-for-byte parity between MCP tool responses and raw httpx calls to the same endpoints. Excluded by default; run explicitly with a real key:

SENS_API_KEY=<a real key> pytest -m live tests/test_live_integration.py -v

License

MIT

Available Tools

4 tools

get_pricesA

Fetch composite electricity prices and rate breakdown for a given OSD + tariff, optionally scoped to a retailer, date, market, region, and annual consumption. When annual_kwh is provided, the backend computes exact annual capacity fees and volume-weighted totals — never re-derive these client-side.

detail_level="summary" (default) strips verbose audit fields for token economy; use detail_level="detailed" for the full raw payload.

ParametersJSON Schema

Name	Required	Default
`osd`	Yes
`date`	No
`page`	No
`size`	No
`since`	No
`market`	No
`region`	No
`taryfa`	Yes
`annual_kwh`	No
`sprzedawca`	No
`detail_level`	No	summary

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral disclosure burden. It explains that annual_kwh triggers backend-side computation and explicitly warns against client-side re-derivation, and it clarifies the difference between summary and detailed outputs. It does not discuss pagination behavior or authentication, but the 'Fetch' verb implies a read operation and core behavior is disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and well-structured: the main purpose is front-loaded, and the second paragraph adds only high-value operational details. Every sentence earns its place, including the warning not to re-derive fees client-side.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter tool with no annotations and zero schema descriptions, the description covers the central workflow but omits pagination semantics, the role of 'since', and how this tool relates to its siblings. The presence of an output schema and clear core behavior makes it usable, but the definition is not fully complete for a complex tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It adds real meaning for annual_kwh and detail_level, and lightly maps sprzedawca to 'retailer' while mentioning date, market, region, and annual consumption as scoping options. However, it does not explain page, size, since, or the exact meaning of osd and taryfa beyond the phrase 'OSD + tariff', leaving several parameters only inferable from names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Fetch') and a precise resource ('composite electricity prices and rate breakdown'), scoped to OSD and tariff. It naturally differentiates this tool from siblings like search_tariffs and get_tariff_components by focusing on composite price retrieval rather than tariff lookup or component extraction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly establishes the main use case: fetch prices for a given OSD and tariff, with optional filters. It gives practical guidance for annual_kwh and detail_level, but does not explicitly mention when not to use this tool or when a sibling would be preferable. Context is clear, but exclusions are absent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_tariff_componentsC

Inspect the detailed fixed/variable rate components of a tariff, as approved by URE (the Polish energy regulator).

ParametersJSON Schema

Name	Required	Description	Default
`since`	No
`tariff_id`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'inspect' which weakly implies a read-only operation, but it does not mention whether the tool returns historical/current data, how 'since' affects behavior, what happens for invalid tariff IDs, or any authorization requirements. The 'as approved by URE' detail adds domain context but no behavioral transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, focused sentence with no fluff. It front-loads the core purpose and includes a relevant regulatory qualifier. Nothing extraneous is present, and it is appropriately brief for a straightforward lookup tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema (which covers return values), the description omits key operational context: the optional 'since' parameter is absent, no usage example or prerequisite is given, and the relationship between this tool and get_prices is unclear. For a tool with two params and zero schema descriptions, this is insufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not mention either parameter. The 'since' parameter is completely unexplained, and even 'tariff_id' gets no elaboration beyond its name. The description provides zero added meaning beyond the input schema's property titles.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Inspect') and resource ('detailed fixed/variable rate components of a tariff'), instantly distinguishing it from siblings like search_tariffs or get_prices. The clarification about URE approval adds regulatory context. This is unambiguous and free of tautology.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for inspecting tariff components, but it gives no explicit guidance on when to choose it over get_prices, resolve_operator, or search_tariffs. There are no stated conditions, exclusions, or alternative pointers. The context is limited to a generic 'this is what it does'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

resolve_operatorA

Resolve a natural-language city or company name to the exact OSD (distribution operator) and default retailer strings the SENS API expects.

Example: query="Kraków" or query="enea". Handles typos via fuzzy matching.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes
`region`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It explicitly discloses the fuzzy-matching typo behavior and the exact-string output expectation. It does not cover edge cases like no-match behavior, but the key behavioral traits are present.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences plus an example line. Every sentence earns its place: purpose, example inputs, and fuzzy behavior are all stated without filler. The most important information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple resolver with an output schema, the description covers purpose, fuzzy behavior, and expected output. The missing region semantics is a real gap, but the overall definition is largely complete and actionable for the common query-only case.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains the query parameter through examples and semantics, but the region parameter is never mentioned at all, leaving one of the two parameters completely undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb 'Resolve' and names both the input (natural-language city/company name) and the output (exact OSD/default retailer strings for the SENS API). This clearly differentiates it from the sibling search/get tariff tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly indicates when to use this tool: when you have a fuzzy or natural-language operator name and need the canonical API strings. It gives concrete examples. It does not explicitly list exclusions or alternative tools, but the intended scenario is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_tariffsA

Discover valid tariff codes tailored to a customer profile (household, small business, or industry), optionally narrowed by zone preference and operator.

ParametersJSON Schema

Name	Required	Description	Default
`operator`	No
`customer_type`	Yes
`zone_preference`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A3.7/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the behavioral burden. 'Discover' implies a read-only search and 'optionally narrowed' describes filtering behavior, but it does not disclose prerequisites such as whether the operator should be resolved first, what happens when no results match, or whether the output is limited to codes rather than prices.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence with no filler. It states the core action first and then the optional modifiers, with every phrase contributing to the agent's understanding of what to pass and why.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a low-complexity search tool with an output schema, the description covers the main operation and filter semantics. But there are no annotations, no guidance on sibling-tool workflows, and no statement about whether customer_type is required or what the default behavior is when optional filters are omitted.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It maps customer_type to a 'customer profile' and clarifies that zone_preference and operator are optional narrowing filters. However, it does not explain what 'operator' means or the semantics behind the zone enum values, so the compensation is only partial.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Discover') and a specific resource ('valid tariff codes'), and clearly scopes the results to a customer profile with optional zone/operator filters. This semantically distinguishes it from sibling tools like get_prices and get_tariff_components, which target different outputs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool: when tariff codes are needed for a customer type, optionally narrowed by zone or operator. However, it provides no explicit when-not-to-use guidance, no mention of alternatives, and does not explain how this tool relates to resolve_operator or get_prices.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

4 tool updatesv0.1.0Aug 26, 2026
- First observedget_prices
- First observedget_tariff_components
- First observedresolve_operator
- First observedsearch_tariffs

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored 2026-08-26 01:10 across 4 tools

Disambiguation5/5

Each tool targets a distinct stage in the workflow: resolution of operator names, tariff discovery, tariff component inspection, and price fetching. No overlapping responsibilities or ambiguous boundaries.

Naming Consistency5/5

All four tools follow a consistent verb_noun pattern with snake_case (resolve_operator, search_tariffs, get_tariff_components, get_prices). The verbs (resolve, search, get) are clear and uniform.

Tool Count5/5

Four tools is well-scoped for a focused API covering Polish energy tariffs and prices. Each tool serves a distinct, necessary function without redundancy or bloat.

Completeness5/5

The tool set provides a complete workflow: resolve an operator, search for tariffs, inspect tariff components, and fetch prices with breakdowns. No obvious gaps or dead ends exist for the stated purpose of retrieving energy pricing information.

Maintenance

ActivityMaintained

ResponsivenessUnresponsive

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Elecz Electricity Price Signal API A
io.github.zemloai-ctrl
Real-time electricity prices for AI agents. 40+ countries, 100+ zones. No auth required.
Energy Home Automation & IoT Research & Data
324
Elecz Electricity Price Signal A
com.elecz
Real-time electricity price signals for AI agents. Spot prices, cheapest hours, and contract recommendations. 31 countries across Europe and Oceania. No authentication required.
Energy Finance Home Automation & IoT
32
strajkpolski-mcp B
io.github.Hei33enberg
Verified Polish open data for AI agents: debt, budget, 460 MPs, votings, judiciary search, RAG.
Government Data Open Data RAG Systems
2
voltcast A
com.voltcast
European day-ahead electricity prices (43 zones), accuracy-published forecasts, carbon, optimize.
Energy Finance
72

Related MCP Servers

mcp-server-eia
Energy Government Data
abrose1
A
license
Not graded
quality
C
maintenance
Provides AI agents with structured access to the U.S. EIA Open Data API for energy data including power plants, operations, fuel prices, projections, and state CO2 emissions.
Updated 6 months ago (2026-03-30 07:46 UTC)
MIT
US ISO Grid MCP
Energy Search
pipeworx-io
A
license
Not graded
quality
C
maintenance
Enables real-time access to US electricity generation, fuel mix, and demand data through natural language queries.
Updated 4 days ago (2026-09-13 13:08 UTC)
5 npm
MIT
Datadis MCP Server
Energy Research & Data
Jaimegruiz
A
license
Not graded
quality
C
maintenance
Enables AI agents to access and analyze Spanish electricity consumption data via the Datadis API, providing tools for supply management, consumption analysis, anomaly detection, and executive reporting.
Updated 2 months ago (2026-07-04 07:48 UTC)
MIT
tibber-mcp-server
Energy Home Automation & IoT
Schimmilab
A
license
A
quality
A
maintenance
Enables querying Tibber electricity prices, forecasts, consumption data, cheapest hours, and live Pulse measurements through natural language.
Updated 6 days ago (2026-09-11 08:04 UTC)
7
MIT

sens-mcp

Quickstart

Run via uvx (recommended, no install step)

Or install with pip

Environment variables

Using it with an AI agent

Claude Desktop

Cursor

Tools exposed

Developer examples (no MCP required)

API reference (essentials)

Development

Live integration suite (opt-in)

License

Available Tools

Output Schema

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Run via `uvx` (recommended, no install step)