Integrates with National Grid's Carbon Intensity API to provide real-time and forecasted CO2 intensity data for the UK, as well as power mix and renewable percentage information.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Energy Grid MCP Server Find the greenest 4-hour window in the next 48 hours for my AI training job."
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.
MCP-Server für Stromnetz-Daten — CO2-Intensität, Strommix, Preise und optimale Zeitfenster für energieintensive KI-Tasks.
CO2-Intensität — Echtzeit-Gramm CO2 pro kWh (UK kostenlos ohne Key, global mit Electricity Maps Key)
Grüne Zeitfenster — Findet die nächsten 48h mit niedrigster CO2-Intensität für GPU-Jobs
Strommix — Anteil Wind, Solar, Atom, Gas, Kohle in Echtzeit
Strompreise — Großhandelspreise Deutschland (SMARD, kein Key) + EU Day-Ahead (ENTSO-E, optionaler Key)
48h Prognose — CO2-Intensitäts-Vorhersage für smarte Task-Planung
Related MCP server: mcp-carbon-intensity
pip install energy-grid-mcp-serverOder mit uvx (kein Install nötig):
uvx energy-grid-server{
"mcpServers": {
"energy-grid": {
"command": "uvx",
"args": ["energy-grid-server"],
"env": {
"ELECTRICITY_MAPS_TOKEN": "optional",
"ENTSOE_TOKEN": "optional"
}
}
}
}Tool | Beschreibung | Key nötig? |
| CO2-Intensität UK (national + regional) | Nein |
| 48h CO2-Prognose UK | Nein |
| Bestes Zeitfenster für AI-Tasks | Nein |
| Strommix UK (Wind, Solar, etc.) | Nein |
| Erneuerbaren-Anteil UK | Nein |
| Großhandelspreis DE (SMARD) | Nein |
| CO2-Intensität weltweit | Electricity Maps |
| Strommix weltweit | Electricity Maps |
| Day-Ahead Preise EU | ENTSO-E |
Electricity Maps (global CO2): api-portal.electricitymaps.com — 100k Calls/Monat kostenlos
ENTSO-E (EU-Preise): transparency.entsoe.eu — kostenlos nach Registrierung
UK-Daten und deutsche Großhandelspreise funktionieren ohne API-Keys.
"Wann ist der beste Zeitpunkt heute für mein GPU-Training? CO2 soll minimal sein."
"Wie hoch ist der aktuelle Anteil erneuerbarer Energien im UK-Stromnetz?"
"Gib mir den aktuellen Großhandelsstrompreis in Deutschland."
"Erstelle einen Plan für meinen Batch-Job in den nächsten 48h mit niedrigstem CO2-Ausstoß."Carbon Intensity UK API — National Grid ESO (kostenlos)
Electricity Maps — Globale Echtzeit-CO2-Daten
SMARD — Bundesnetzagentur Strommarkt-Daten
ENTSO-E — Europäische Übertragungsnetzbetreiber
Category | Servers |
🔗 Blockchain | |
🌍 Data | Weather · Germany · Agriculture · Space · Aviation · EU Companies |
🔒 Security | |
🤖 Agent Infra | Memory · Directory · Hub · Reputation |
🔬 Research |
MIT — AiAgentKarl
Findet das grünste Zeitfenster für energieintensive AI-Tasks (UK).
Ideal für: GPU-Training, Batch-Verarbeitung, große Inferenz-Jobs.
Args: duration_hours: Dauer des geplanten Tasks in Stunden. Standard: 2.
Returns: Bestes Zeitfenster mit niedrigster CO2-Intensität in den nächsten 48 Stunden inkl. Vergleich zu aktuellem Wert.
| Name | Required | Description | Default |
|---|---|---|---|
| duration_hours | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, but description clearly states it returns the best time window with lowest CO2 intensity in next 48 hours plus comparison to current value. Does not disclose potential accuracy limitations or reliance on forecast data, but provides essential behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Concise German description with clear sections: purpose, ideal uses, parameters, returns. No fluff, every sentence adds value. Front-loaded with action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, but description covers return value (time window with CO2 comparison). Could specify output format (e.g., timestamp range), but sufficient for effective tool use. Sibling tools contextually differentiate this as a scheduling optimizer.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% description coverage, but description explains the sole parameter 'duration_hours' as task duration in hours with default of 2. Adds meaningful context beyond schema type and default value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clear verb 'findet' (finds) and resource 'grünste Zeitfenster' (greenest time window) with specific use case for AI tasks in UK. Differentiates from sibling tools that provide current or forecast carbon intensity values rather than optimal scheduling windows.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
States ideal use cases: GPU training, batch processing, large inference jobs. However, does not explicitly mention when not to use or contrast with alternatives like get_uk_carbon_intensity (which gives current values) or get_carbon_intensity_forecast (which gives forecast series).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
CO2-Intensitäts-Prognose für das UK-Stromnetz (bis 48h voraus).
Args: hours_ahead: Stunden in die Zukunft (max. 48). Standard: 24.
Returns: Liste mit stündlichen CO2-Prognosen — ideal um energieintensive Tasks in grüne Zeitfenster zu planen.
| Name | Required | Description | Default |
|---|---|---|---|
| hours_ahead | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It only mentions the time horizon and return format, but lacks details on data freshness, update frequency, API limits, or potential rate limiting. This is a gap for a tool with no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: a brief one-liner for purpose, followed by parameter details, return format, and a use case. Every sentence provides value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has one parameter, no output schema, and multiple siblings, the description covers the main functionality and usage. However, it could be more complete by explicitly distinguishing from get_uk_carbon_intensity and mentioning data source or update frequency.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate. It explains hours_ahead with default (24) and max (48), and describes the return value as a list of hourly forecasts. This adds meaning beyond the schema's minimal information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool provides a CO2 intensity forecast for the UK power grid up to 48 hours ahead. The verb 'get' and resource 'carbon intensity forecast' are specific, and it distinguishes from siblings like get_uk_carbon_intensity (likely current) and find_greenest_time_window (different purpose).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the parameter hours_ahead with default and max, and states the return format is a list of hourly forecasts. It gives a use case: planning energy-intensive tasks. However, it does not explicitly compare to sibling tools or state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Day-Ahead Strompreise für EU-Länder (benötigt ENTSOE_TOKEN).
Args: country_code: EIC-Ländercode, z.B. 'DE', 'FR', 'ES', 'IT', 'PL'.
Returns: Stündliche Day-Ahead Preise für morgen in EUR/MWh. Benötigt ENTSOE_TOKEN aus https://transparency.entsoe.eu registrieren.
| Name | Required | Description | Default |
|---|---|---|---|
| country_code | No | DE |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but the description covers authentication token, return unit (EUR/MWh), and time horizon (next day). It adequately describes behavior for a simple data retrieval tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with three short sections: purpose, args, returns. No wasted words, and critical info (token requirement) is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given a single parameter, no output schema, and simple behavior, the description provides sufficient context: what it does, what param means, what it returns, and prerequisite (token).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The sole parameter country_code is explained as EIC code with examples (DE, FR, etc.), adding meaning beyond the schema which only has type and default. Schema coverage is 0%, and the description fully compensates.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves day-ahead electricity prices for EU countries, specifying the token requirement. It distinguishes from siblings like get_germany_wholesale_price and carbon intensity tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the token requirement and provides example country codes. It implies usage for EU day-ahead prices vs alternatives, but lacks explicit when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Aktueller Großhandelsstrompreis Deutschland (EUR/MWh) von SMARD.
Keine Registrierung nötig — direkt aus Bundesnetzagentur-Daten.
Returns: Aktueller Preis in EUR/MWh, Zeitraum, Quelle.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses the data source (SMARD/Bundesnetzagentur), states that no registration is needed (indicating open access), and lists the returned fields (price, time period, source). For a simple read-only tool with no parameters, this provides sufficient behavioral transparency beyond the name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: three short lines covering output, access, and return fields. Every sentence serves a purpose, and the structure is well-organized with a clear separation of concerns.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no parameters, no output schema), the description provides essential information: what is returned, the unit, and the source. It could specify the exact time resolution (e.g., current hour), but it is largely complete for a straightforward data retrieval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has no parameters, and the schema coverage is 100% (trivially). The description adds no parameter-specific information because none exist. The baseline score of 3 is appropriate as the description correctly confirms the tool requires no input.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves the current wholesale electricity price for Germany in EUR/MWh from SMARD/Bundesnetzagentur. It uses a specific verb ('get'), a specific resource ('wholesale price'), and the domain (Germany) distinguishes it from sibling tools that deal with carbon intensity, power mix, or EU-wide prices.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description notes that no registration is required, which is a practical usage hint. While it does not explicitly compare with siblings or list exclusions, the tool's specific purpose (German wholesale price) is clearly differentiated from the carbon and power mix tools listed as siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
CO2-Intensität für eine globale Zone (benötigt ELECTRICITY_MAPS_TOKEN).
Args: zone: Zone-Code, z.B. 'DE' (Deutschland), 'FR' (Frankreich), 'US-CAL-CISO' (Kalifornien), 'IN-NO' (Nordindien).
Returns: CO2-Intensität (gCO2/kWh) und Strommix für die Zone. Benötigt ELECTRICITY_MAPS_TOKEN in .env.
| Name | Required | Description | Default |
|---|---|---|---|
| zone | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that the tool returns CO2 intensity and power mix, and requires a token. This is sufficient for a read-only tool with no side effects mentioned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two short paragraphs. The first sentence immediately states the purpose, followed by parameter details. No extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the purpose, parameter, and token requirement. However, it does not detail the response structure beyond stating it returns CO2 intensity and power mix. For a simple tool with one parameter, this is mostly adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides only the parameter name 'zone' with no description (0% coverage). The description compensates fully by providing concrete examples and explaining the format, adding significant meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it gets CO2 intensity for a global zone, specifying the verb and resource. It differentiates from sibling tools by focusing on global zones rather than specific countries like UK or Germany.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions the required ELECTRICITY_MAPS_TOKEN, which is a necessary condition. However, it does not explicitly state when to use this tool versus alternatives like get_uk_carbon_intensity or get_global_power_mix, leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Strommix für eine globale Zone (benötigt ELECTRICITY_MAPS_TOKEN).
Args: zone: Zone-Code, z.B. 'DE', 'FR', 'ES', 'US-CAL-CISO'.
Returns: Aufschlüsselung der Stromerzeugung nach Quelle (MW).
| Name | Required | Description | Default |
|---|---|---|---|
| zone | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the authentication requirement (ELECTRICITY_MAPS_TOKEN) and the return format (breakdown by source in MW). However, it does not mention rate limits, idempotency, or any destructive behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with a clear structure: a short sentence followed by Args and Returns sections. No extraneous text. However, it mixes German and English, which could be slightly confusing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has one parameter, no output schema, and no annotations, the description adequately covers the parameter, return value, and authentication. It could be improved by referencing relevant sibling tools for better context, but it is still complete enough for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'zone' is described with examples ('DE', 'FR', 'ES', 'US-CAL-CISO') and explained as a zone code. This adds significant meaning beyond the schema's title and type. Schema description coverage is 0%, but the tool description compensates well.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool retrieves the power mix for a global zone, requiring a token. It distinguishes from sibling tools like get_uk_power_mix by specifying 'global zone' and providing examples such as DE, FR, US-CAL-CISO. However, it lacks an explicit verb like 'retrieve' or 'get'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates usage by providing zone examples and requiring a token. However, it does not explicitly state when to use this tool over alternatives such as get_global_carbon_intensity or find_greenest_time_window. Usage context is implied but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Prozentualer Anteil erneuerbarer Energien im UK-Stromnetz.
Args: region: Optional — UK-Region für regionalen Vergleich.
Returns: Aktueller Anteil erneuerbarer Energien inkl. Trend-Einschätzung.
| Name | Required | Description | Default |
|---|---|---|---|
| region | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist. The description provides minimal behavior: returns current share and trend assessment. No info on data source, update frequency, or whether it's destructive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences and a structured Args/Returns section. However, it is in German while the tool name and parameter are English, causing inconsistency.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists. The description does not specify the return format (e.g., percentage number, string). For a simple tool, it lacks detail on what exactly is returned.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaning to the region parameter as 'for regional comparison,' but it is brief. Schema coverage is 0%, so the description partially compensates.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool gets the renewable percentage in the UK grid, which is clear. However, it does not distinguish it from sibling tools like get_uk_power_mix that may also include renewable data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. The only usage hint is that the region parameter is optional for regional comparison.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Aktuelle CO2-Intensität des britischen Stromnetzes (gCO2/kWh).
Args: region: Optional — UK-Region (z.B. 'South West England', 'Scotland'). Leer lassen für nationale Übersicht.
Returns: CO2-Intensität (gCO2/kWh), Index (low/moderate/high/very high), Strommix-Aufschlüsselung nach Quelle.
| Name | Required | Description | Default |
|---|---|---|---|
| region | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavior. It explains the return values (intensity, index, mix breakdown) and implies a read-only operation. It lacks details on data freshness or update frequency but is adequate for a data retrieval tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with clear Args and Returns sections. Every sentence provides valuable information without unnecessary verbosity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and lack of output schema, the description adequately explains return values. It is complete for an AI agent to understand input, output, and side effects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter (region) with 0% description coverage. The description explains the parameter's purpose, optionality, and provides example values, adding significant meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it provides current CO2 intensity of the UK power grid with units (gCO2/kWh). It distinguishes from siblings by specifying UK focus and optional regional filtering, making it unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates that leaving the region field empty gives national overview, guiding usage. However, it does not explicitly state when to use this tool versus alternatives like get_uk_power_mix or get_global_carbon_intensity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Aktueller Strommix des britischen Netzes — Erneuerbare vs. Fossil.
Returns: Anteil jeder Energiequelle (%) inkl. Wind, Solar, Nuclear, Gas, Coal. Keine API-Registrierung nötig.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It clearly states the output (percentage shares of sources) and implied read-only nature. For a simple, no-parameter tool, this is sufficient transparency, though it lacks mention of potential latency or caching.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: two short sentences that front-load the main purpose and then detail the return value and a usage note. No superfluous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters and no output schema, the description fully explains what the tool returns (energy source percentages) and provides a helpful note about no registration. It is complete for its complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no parameters (0 params), so baseline score is 4. The description correctly focuses on the output and does not need to elaborate on parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it returns the current UK power mix with percentage shares for each energy source (Wind, Solar, Nuclear, Gas, Coal). The verb 'get' and resource 'uk power mix' are specific, and the tool is distinct from siblings like 'get_uk_carbon_intensity' and 'get_renewable_percentage_uk' which focus on narrower metrics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates it provides the current mix and notes no API registration is needed, which guides usage. However, it does not explicitly mention when not to use this tool versus alternatives, though the simplicity of the tool (no parameters) reduces ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0find_greenest_time_windowget_carbon_intensity_forecastget_eu_day_ahead_pricesget_germany_wholesale_priceget_global_carbon_intensityget_global_power_mixget_renewable_percentage_ukget_uk_carbon_intensityget_uk_power_mixMost tools have distinct purposes (UK carbon, global carbon, prices, power mix), but there is some overlap between get_renewable_percentage_uk and get_uk_power_mix, and between get_uk_carbon_intensity and get_carbon_intensity_forecast. Descriptions help differentiate, but ambiguity is possible.
Names are inconsistent: most start with 'get_', but one starts with 'find_'. Some include country prefix ('uk', 'germany', 'eu') while others use 'global'. This mix of conventions reduces predictability.
With 9 tools, the server covers a reasonable scope for energy grid data, including UK and global carbon intensity, power mix, and prices. The count feels appropriate—not too sparse or bloated.
The server covers current and forecasted carbon intensity, power mix, and prices, but lacks historical data and more granular queries (e.g., specific generation types). The 'find_greenest_time_window' tool is a nice addition, but there are noticeable gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Real-time electricity prices for AI agents. 40+ countries, 100+ zones. No auth required.
Real-time electricity price signals for AI agents. Spot prices, cheapest hours, and contract recommendations. 31 countries across Europe and Oceania. No authentication required.
Live and historical electricity prices and demand for 25 grids; carbon intensity for GB.
Carbon MCP — UK Carbon Intensity API (free, no auth)
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/AiAgentKarl/energy-grid-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server