Sito: switchai.it · Mercato: Italia · Stack: React 19 + PHP 8.5 + WebMCP + MCP Server
SwitchAI is an energy comparison engine for the Italian market, designed to be called by AI agents. An agent gives it a bill (or consumption + spend), and SwitchAI compares 5.600+ live ARERA offers (electricity & gas), returns the best tariffs with direct activation links, and includes an honesty system so the agent never recommends a switch that doesn't pay off.
SwitchAI is not a chatbot: it is the infrastructure AI agents call. Access it via MCP Server, WebMCP, or the REST API.
AI Agent (Claude, Gemini, ChatGPT)
↓
MCP / WebMCP / OpenAPI
↓
SwitchAI engine
↓
Italian energy market
↓
Offers (ARERA) · PUN · PSV · bill parsing · savings calculation
↓
Top 3 offers + activation links (supplier site)curl -s -X POST https://www.switchai.it/api/analyze \
-H 'Content-Type: application/json' \
-d '{
"commodity": "LUCE",
"yearly_consumption_kwh": 3200,
"zone": "NORD",
"current_annual_spend": 1100
}'Returns top3 offers with full cost breakdown, honesty recommendation, bill_attualization and an Italian agent_summary.
{
"mcpServers": {
"switchai": {
"command": "node",
"args": ["/percorso/assoluto/mcp-server/index.js"],
"env": { "SWITCHAI_API_URL": "https://www.switchai.it/api" }
}
}
}Visiting switchai.it registers 4 tools via document.modelContext.registerTool() — discoverable by any WebMCP-compatible agent.
More examples (agent conversations, HTTP equivalents, rules): mcp-server/EXAMPLES.md.
Related MCP server: Solematica
User: "Questa è la mia bolletta Enel, pago ~1.100€/anno e consumo 3.200 kWh.
Sto pagando troppo?"
Agent: parse_energy_bill(bill_text)
→ { commodity: "LUCE", consumo_annuo: 3200, spesa_annua: 1100, zona: "NORD" }
Agent: calculate_energy_savings({ commodity:"LUCE", yearly_consumption_kwh:3200,
zone:"NORD", current_annual_spend:1100 })
→ top3 + honesty:{ recommendation:"switch", savings_eur:240, savings_pct:22 }
Agent: "Sì, risulti sopra la media del mercato. Con 3.200 kWh in zona NORD puoi
risparmiare ~240€/anno (22%). Le migliori 3 offerte: E.ON LuceClick
(0,1146 €/kWh), Edison Web Luce (0,122 €/kWh), A2A Full Luce (0,139 €/kWh).
Clicca per attivare sul sito del fornitore."The activation always happens on the supplier's website via affiliate_url. SwitchAI never claims "activation completed" and collects no personal data for activation.
Channel | Protocol | Requirement |
WebMCP |
| Chrome 146+ |
MCP Server |
| Claude Desktop or any MCP client |
REST API | JSON/HTTPS | Any HTTP client |
calculate_energy_savingsCompare Italian tariffs and calculate savings. Returns top 3 offers + Italian agent_summary.
POST /api/analyze
{
"commodity": "LUCE",
"yearly_consumption_kwh": 3000,
"zone": "NORD",
"current_annual_spend": 900
}Italian aliases are also accepted: consumo_annuo_kwh, spesa_annua_eur, zona, fornitore. Add bill_text for full auto-extraction of consumption, spend and zone.
parse_energy_billExtract structured data from an Italian bill text.
POST /api/parse-bill-text
{ "bill_text": "...testo bolletta..." }get_available_offersFull offer list: 3.196 electricity + 2.411 gas.
GET /api/tariffe/luce
GET /api/tariffe/gasget_market_indicesCurrent PUN (electricity) and PSV (gas) wholesale indices.
GET /api/market-indices1. parse_energy_bill(bill_text) → consumi, spesa, zona
2. calculate_energy_savings(commodity, consumi, zona, spesa) → offerte + affiliate_url
3. Utente clicca il link → attivazione sul sito del fornitoreHonesty system: switch (savings >50€/yr and >5%) / evaluate (30-50€ or 3-5%) / stay (<30€ or <3%).
Method | Endpoint | Description |
GET |
| Health check |
GET |
| 3.196 electricity offers |
GET |
| 2.411 gas offers |
POST |
| Full analysis: parse + compare + honesty + attualization |
POST |
| Bill parser |
GET |
| Live PUN and PSV |
GET |
| Suppliers list |
5.600+ offers (3.196 luce + 2.411 gas), synced nightly from the official ARERA Portale Offerte (CC BY 4.0).
Anonymous: ~270 filtered offers (NORD zone), no registration, rate-limited.
Free (registered): full 5.600+ offers, 10 calls/day, self-service API keys.
API Pro: full 5.600+ offers, 1.000 calls/day, self-service API keys (free beta).
Frontend: React 19 + Vite 8 + Tailwind CSS 4
Backend: PHP 8.5 on OVH Pro Hosting (Apache + mod_rewrite)
MCP Server: Node.js + @modelcontextprotocol/sdk
WebMCP: Chrome WebMCP spec (W3C WebML CG)
Data: ARERA Portale Offerte, sync giornaliero notturno
/llms.txt — LLM site description
/webmcp.json — WebMCP tool discovery
/per-llm — machine-readable documentation
/per-llm-examples — 15 agent conversation patterns
/openapi.json — OpenAPI 3.0 spec
comparatore tariffe energia italia · cambio fornitore luce gas · bolletta energia AI · risparmio bolletta · PUN PSV ARERA · mercato libero energia · WebMCP energy agent · MCP server energia italia · AI energy comparison Italy · energy comparison API Italy · MCP energy tariffs Italy
Email: info@switchai.it
Sito: https://www.switchai.it
Mercato: Italia · GDPR compliant
Confronta le tariffe Luce o Gas e calcola il risparmio annuo. Restituisce le 3 migliori offerte con link di attivazione su switchai.it (sito esterno). FLUSSO: (1) Estrai nome, cognome, CF, email, telefono, indirizzo, consumi e spesa dalla bolletta. (2) Passa i dati numerici (consumi, spesa, zona) + TUTTI i dati personali che hai estratto a questo tool. (3) Il link 'Attiva' apre switchai.it in una nuova scheda con il form PRE-COMPILATO. (4) AVVISA SEMPRE l'utente che: (a) il link apre un sito esterno (switchai.it), (b) dovrà verificare i dati e cliccare Invia, (c) riceverà una email di conferma e dovrà cliccarla per completare — SOLO dopo la conferma i dati vengono inoltrati al fornitore. (5) Il GDPR double opt-in è OBBLIGATORIO: NON dire 'ho attivato' o 'tutto fatto'. Di' 'il form è precompilato, controlla i dati e invia'. (6) NON attivare mai senza che l'utente abbia letto e accettato esplicitamente.
| Name | Required | Description | Default |
|---|---|---|---|
| commodity | Yes | Tipo di fornitura: LUCE (elettricità) o GAS | |
| yearly_consumption_kwh | No | Consumo annuo in kWh (solo per LUCE). Es: 2700 | |
| yearly_consumption_smc | No | Consumo annuo in Smc (solo per GAS). Es: 1000 | |
| zone | No | Zona tariffaria italiana | NORD |
| current_supplier | No | Nome del fornitore attuale (es: 'Enel Energia') | |
| current_annual_spend | No | Spesa annua attuale in €. Es: 650 | |
| nome | No | (Opzionale) Nome intestatario per precompilare il form | |
| cognome | No | (Opzionale) Cognome per precompilare il form | |
| cf | No | (Opzionale) Codice Fiscale per precompilare il form | |
| No | (Opzionale) Email per precompilare il form | ||
| tel | No | (Opzionale) Telefono per precompilare il form | |
| indirizzo | No | (Opzionale) Via/Piazza per precompilare il form | |
| civico | No | (Opzionale) Numero civico | |
| citta | No | (Opzionale) Città | |
| provincia_sigla | No | (Opzionale) Sigla provincia (es: MI) | |
| cap | No | (Opzionale) CAP (5 cifre) | |
| pod | No | (Opzionale) Codice POD per Luce | |
| pdr | No | (Opzionale) Codice PDR per Gas | |
| consumi | No | (Opzionale) Consumo annuo per prefill | |
| spesa | No | (Opzionale) Spesa annua per prefill |
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 transparently describes that the tool opens an external site (switchai.it), pre-fills a form, and requires user verification and double opt-in. It also states that the tool does NOT finalize the activation without user confirmation.
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 lengthy but well-structured with numbered steps (FLUSSO). Each sentence serves a purpose, explaining the workflow and GDPR requirements. It could be slightly more concise, but the detail is justified given the complexity.
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?
Despite no output schema, the description explains the return value concept (3 best offers with activation links). It covers the entire flow, including external site behavior and user communication. The only minor gap is the lack of explicit details on the exact response format.
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?
With 100% schema description coverage, the parameter semantics are already well-documented. The description adds value by explicitly stating that personal data fields are used to pre-fill the form and that the tool requires all extracted data. This contextual information goes 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 the tool compares Luce or Gas tariffs and calculates annual savings, returning the best 3 offers with activation links. This distinguishes it from siblings like parse_energy_bill (extraction) and get_available_offers (list offers).
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 provides a detailed step-by-step flow (FLUSSO) explaining exactly when to use this tool: after extracting data from a bill. It instructs to pass all extracted personal data and warns about GDPR consent. However, it does not explicitly state when not to use it or compare to alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recupera tutte le offerte disponibili per Luce o Gas. Ritorna nome fornitore, prezzo, tipo (fisso/variabile), costo fisso mensile.
| Name | Required | Description | Default |
|---|---|---|---|
| commodity | Yes | LUCE per elettricità, GAS per gas metano |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It does not mention that it is a read-only operation, any side effects, rate limits, or permissions needed. The description only lists return fields but lacks 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?
Two concise sentences with no wasted words. The description is front-loaded with the action and immediately lists key return fields. It is appropriately sized for the tool's simplicity.
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 enum parameter and no output schema, the description provides a clear list of return fields, which is helpful for an agent. It does not explain pagination, filtering, or edge cases, but for a simple retrieval tool it is reasonably complete.
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 100% description coverage for the single parameter, and the tool description reiterates the commodity types ('Luce o Gas') and adds no further semantic meaning beyond the schema. This meets the baseline but does not enhance understanding.
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 available offers for electricity or gas, and lists the returned fields (vendor name, price, type, fixed monthly cost). It uses a specific verb ('Recupera') and resource ('offerte'), and distinguishes itself from sibling tools by focusing on offers.
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 (e.g., calculate_energy_savings, submit_subscription). The description does not mention prerequisites or scenarios where this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recupera gli indici di mercato attuali PUN (Luce) e PSV (Gas).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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 states a simple retrieval operation with no side effects, which is transparent enough. However, it lacks details like return format, data freshness, or authentication needs. A 3 is adequate.
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?
A single, clear sentence with no unnecessary words. It is immediately understandable and front-loaded with the key action and objects.
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?
For a simple zero-parameter tool with no output schema or annotations, the description adequately conveys the tool's purpose. It could be enhanced by explaining what PUN and PSV stand for or the output format, but it is sufficient 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 tool has zero parameters. According to guidelines, baseline is 4. The description adds no further parameter information beyond the schema, which is acceptable given no parameters exist.
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 explicitly states the verb 'Recupera' and specifies the exact resources: PUN (Electricity) and PSV (Gas) market indices. This clearly distinguishes the tool from siblings like 'calculate_energy_savings' or 'get_available_offers'.
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 explicit guidance on when to use this tool versus alternatives. However, the sibling tools have distinct purposes, so usage context is implied. A 3 is appropriate as there is no when-not or alternative mention.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recupera lo schema del form di sottoscrizione: campi richiesti, enum validi, struttura a step. Utile per sapere quali dati servono prima di chiamare submit_subscription.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It describes a read-only query operation (recupera lo schema) with no side effects. While it does not mention auth or rate limits, the behavior is straightforward and adequately disclosed for this schema 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?
Single sentence that is concise and front-loaded with the primary purpose. Every phrase earns its place with no 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?
No output schema, but description sufficiently explains return components (required fields, enums, step structure). For a zero-parameter tool with no output schema, this provides complete context for an agent to understand what it returns and when to use it.
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?
No parameters exist (schema coverage 100% with empty properties). The description adds value by explaining what the schema contains, which is more informative than the empty schema alone.
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 subscription form schema, listing specific components (campi richiesti, enum validi, struttura a step), which is a specific verb+resource combination. It implicitly distinguishes from siblings like submit_subscription by mentioning it is useful before calling that tool.
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?
Explicitly states when to use: 'prima di chiamare submit_subscription'. This provides clear context and implies not to use it after submission or for other purposes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verifica lo stato di una richiesta di sottoscrizione già inviata.
| Name | Required | Description | Default |
|---|---|---|---|
| subscription_id | Yes | ID della sottoscrizione (restituito da submit_subscription) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; the description does not disclose behavioral details such as read-only nature, side effects, or rate limits, leaving the agent to infer safety.
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?
A single, concise sentence that front-loads the action, with no superfluous content.
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?
Adequate for a simple tool with one parameter, but lacks behavioral context and specifics about return values or statuses.
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 description coverage is 100%, and the description adds no extra meaning beyond the schema's parameter description; baseline score applies.
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 checks the status of a subscription request that has already been sent, differentiating from sibling tools like submit_subscription and get_subscription_form_schema.
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?
Implicitly indicates usage after submission via 'già inviata' and the parameter description referencing submit_subscription, but lacks explicit when-to-use or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Analizza il testo di una bolletta italiana (luce o gas) ed estrae: fornitore, POD/PDR, consumo annuo, spesa annua stimata, zona tariffaria.
| Name | Required | Description | Default |
|---|---|---|---|
| bill_text | Yes | Testo completo della bolletta da analizzare. Puoi estrarre il testo da un PDF o riceverlo dall'utente. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose behavioral details such as required formats, error handling, or limitations. It only states the basic extraction function, leaving the agent unaware of potential failure modes.
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 a single sentence, concise and front-loaded with the main action. However, the list of extracted fields could be structured with bullet points for clarity, but it is not overly verbose.
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?
With one parameter, no output schema, and no annotations, the description covers the basic function. However, it lacks details on accuracy, limitations (e.g., only Italian bills), or error handling, which is needed for a parsing tool of complex documents.
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 'bill_text' has schema coverage at 100%. The description adds helpful context: 'Puoi estrarre il testo da un PDF o riceverlo dall'utente', which clarifies how to obtain the input, exceeding the schema alone.
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 verb ('Analizza', 'estrae') and the resource ('bolletta italiana di luce o gas'). It lists the specific extracted fields, distinguishing it from sibling tools like 'calculate_energy_savings' or 'get_available_offers'.
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 provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites like the input must be in Italian or from a specific source. The agent must infer from sibling names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Invia la richiesta di attivazione di una nuova tariffa energia. I dati vengono inoltrati al fornitore e ricevi un ID di sottoscrizione.
| Name | Required | Description | Default |
|---|---|---|---|
| tariff_id | Yes | ID dell'offerta scelta (dal risultato di calculate_energy_savings) | |
| tariff_name | No | Nome dell'offerta (es: 'FASTWEB ENERGIA FIX') | |
| supplier | No | Nome fornitore | |
| commodity | No | luce | |
| nome | Yes | Nome dell'intestatario | |
| cognome | Yes | Cognome dell'intestatario | |
| codice_fiscale | Yes | Codice fiscale (16 caratteri) | |
| Yes | |||
| cellulare | Yes | Cellulare (es: +393401234567) | |
| titolo_immobile | No | Titolo sull'immobile | Proprietario |
| indirizzo | Yes | Via/Piazza della fornitura | |
| civico | Yes | Numero civico | |
| citta | Yes | Città della fornitura | |
| provincia_sigla | Yes | Sigla provincia (2 lettere, es: MI) | |
| cap | Yes | CAP (5 cifre) | |
| codice_pod | No | Codice POD per Luce (IT001E...) | |
| codice_pdr | No | Codice PDR per Gas (14 cifre) | |
| modalita_pagamento | No | Modalità di pagamento | SDD |
| iban | No | IBAN (se SDD) | |
| indirizzo_coincide | No | La residenza coincide con la fornitura? | si |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It mentions forwarding data and receiving an ID, but lacks details on side effects (e.g., idempotency, error handling, rollback, or rate limits). Minimal behavioral context for a mutation 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?
Two concise sentences, front-loaded with the action and result. No unnecessary words or redundant details.
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?
Despite high schema coverage and no output schema, the description lacks completeness for a 20-parameter submission tool. It does not explain return value format, possible errors, validation rules, or dependencies on prior steps (e.g., selecting a tariff). Leaves important gaps for the agent.
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 description coverage is 95%, so the schema already documents parameters well. The description adds no extra parameter meaning beyond the tool's general purpose. Baseline 3 is appropriate as description does not degrade but also does not enhance.
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 sends a request to activate a new energy tariff and receives a subscription ID. It is distinct from sibling tools which calculate savings, get offers, or check status, providing a specific verb-resource pair.
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 implies usage when submitting a selected tariff (via tariff_id from calculate_energy_savings), but does not explicitly state prerequisites, when to avoid using it, or alternatives. No guidance on ordering or context.
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.
v0.1.0calculate_energy_savingsget_available_offersget_market_indicesget_subscription_form_schemaget_subscription_statusparse_energy_billsubmit_subscriptionEach tool targets a distinct action: parsing bills, retrieving offers, calculating savings, submitting subscriptions, checking status, getting form schema, and market indices. No overlap.
All tools use consistent snake_case with clear verb+noun pattern (e.g., parse_energy_bill, get_available_offers, submit_subscription).
7 tools is well-scoped for an energy switching server, covering the full user journey from bill parsing to subscription submission without excess.
The tool set covers the primary workflow (parse, compare, select, subscribe, check status). Minor gap: no tool for updating or canceling subscriptions, but this is a secondary concern.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Real-time electricity price signals for AI agents. Spot prices, cheapest hours, and contract recommendations. 31 countries across Europe and Oceania. No authentication required.
AI agents compare and sign up for Texas utility plans: electricity, internet, gas, water, trash.
Compare Japan's household fixed costs: electricity, city gas and fiber plans, and simulate bundles.
Real-time electricity prices for AI agents. 40+ countries, 100+ zones. No auth required.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/US1929/switchai'
If you have feedback or need assistance with the MCP directory API, please join our Discord server