李茶的茶 · Servidor MCP de pedidos de Qimai. Permite que la IA busque tiendas, consulte menús, arme pedidos y calcule precios en la conversación; si se activa la capacidad de pedido, también puede realizar pedidos reales en nombre del cliente, y el pago siempre lo completa el propio cliente en el miniprograma de 李茶.
Instalación por defecto = solo lectura: sin activar el interruptor, el comportamiento es idéntico a la fase uno: no se genera ningún pedido, no se toca dinero y no se leen datos de negocio.
Dile a tu IA:
Quiero tomar 李茶的茶, tira de GitHub: lichadecha/licha-order-mcp
Una vez instalado, basta con preguntar «¿qué tés con leche tenéis?» o «¿qué tienda me queda más cerca?». Por ahora solo se admite pedido en tienda (comer en el local / para llevar).
¿Es tu primera vez y no sabes qué elegir? Pregunta directamente «¿qué me recomendáis?». Si quieres que la IA te ayude a calcular qué tienda te queda más cerca, también puedes instalarle un MCP de Mapas de Gaode (opcional).
Related MCP server: @striderlabs/mcp-chipotle
Fusiona el siguiente bloque en tu configuración de MCP (mcpServers):
"licha-order-mcp": {
"command": "npx",
"args": ["-y", "github:lichadecha/licha-order-mcp#v0.5.1"]
}Instala el SKILL.md de la raíz de este repositorio en tu directorio de habilidades/instrucciones (cuando el cliente sea compatible con skills).
Reinicia o recarga el MCP según los requisitos de tu cliente.
Indica al usuario que la instalación ha terminado y empieza a servir según las reglas de SKILL.md (la primera frase debe aclarar: solo pedido en tienda / comer en el local / para llevar).
Se requiere Node ≥ 18; en la primera ejecución se compila automáticamente (prepare → tsc). Si npx no lo encuentra, usa la ruta absoluta del directorio de instalación de Node.
Herramienta | Función |
find_store | Busca tiendas por nombre / centro comercial / ciudad; devuelve storeId, estado de apertura y horario |
get_menu | Consulta el menú: sin keyword devuelve categorías; con keyword devuelve la lista de productos |
get_item_detail | Ficha del artículo: especificaciones, preparación (temperatura / dulzor), extras y si está agotado |
preview_order | Arma el pedido y calcula el precio estimado (acumulación local; el importe real lo fija la caja de la tienda / el pedido) |
Al definir la variable de entorno LICHA_ENABLE_ORDERING=1 se registran además 5 herramientas relacionadas con pedidos (bind_member / prepare_order / place_order / get_order_status / my_orders); las restricciones de seguridad se detallan en «Límites de seguridad» más abajo.
Configuración de mcpServers:
{
"mcpServers": {
"licha-order-mcp": {
"command": "npx",
"args": ["-y", "github:lichadecha/licha-order-mcp#v0.5.1"]
}
}
}El comando de instalación apunta fijo a la etiqueta de versión (#v0.5.1), sin seguir la última confirmación; al actualizar, usa la etiqueta indicada en el nuevo README.
Se requiere Node ≥ 18; en la primera instalación se compila automáticamente (el hook prepare ejecuta tsc).
Este servicio lee las credenciales de la plataforma abierta de Qimai desde la máquina local; las credenciales no entran en este repositorio, ni en la configuración, ni en los registros:
Llavero de macOS: openKey de la entrada qmai-cli (desempaquetado automático)
~/.config/qmai/config.yaml: openId / grantCode del perfil activo
También se pueden sobrescribir con variables de entorno: QMAI_OPEN_KEY / QMAI_OPEN_ID / QMAI_GRANT_CODE. Si faltan credenciales, las llamadas a herramientas devuelven «credenciales incompletas»; el servicio en sí arranca con normalidad.
Por defecto no se registra ninguna herramienta de escritura (solo se registran con LICHA_ENABLE_ORDERING=1); sin activarlo, tools/list solo muestra 4 herramientas de solo lectura y el canal de escritura es físicamente inalcanzable.
Una vez activado, la lista blanca de escritura está codificada con una sola entrada (crear pedido); todo lo que esté fuera de la lista blanca se corta físicamente.
El pedido pasa obligatoriamente por una confirmación en dos fases: la IA primero lee el pedido pendiente de confirmar al cliente → el cliente confirma → solo entonces se envía; los parámetros del pedido los ensambla y registra el servidor, y la IA solo tiene un token de un solo uso de 5 minutos, sin poder modificar el contenido del pedido.
Barreras duras: ≤100 ¥ por pedido, ≤5 pedidos por cliente al día / ≤10 en total al día; nunca se paga en nombre del cliente: el pago siempre lo completa el cliente en el miniprograma de 李茶.
Tres registros de auditoría separados (lectura / escritura / acceso); los valores de identificación solo conservan los últimos dígitos.
Las salidas solo proyectan campos públicos (nombre de tienda / dirección / estado de apertura / precio de producto); no se emiten datos de negocio como el contacto del encargado o los costes.
npm install
npm run smoke:mcp
npm run smokeLa serie smoke también incluye smoke:store / smoke:menu / smoke:detail / smoke:order. Las pruebas de humo usan interfaces reales de solo lectura (clase básica 0,1 ¥ por cada 100 llamadas, dentro de la cuota gratuita de 100 000 llamadas al mes; una verificación no supera las 30 llamadas).
La parte de código (src/, scripts/, test/, archivos de configuración) usa Apache-2.0; la parte de texto (SKILL.md, README y demás documentación) usa CC BY-ND 4.0. El nombre y el logotipo de «李茶的茶» pertenecen a la marca y no están cubiertos por ninguna licencia. Ver LICENSE.
按店名、商场名或城市找李茶的茶门店，返回 storeId（看菜单/点单都要用）、营业状态；唯一命中时附营业时间。点单第一步先找店。
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | 店名/商场/城市，如「深圳湾」「太古里」「北京」 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full burden. It clearly describes the tool's behavior: queries by name/mall/city, returns storeId and status, and optionally business hours. No side effects are mentioned but none are implied.
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. First sentence covers functionality and return values; second sentence provides critical contextual guidance ('first step of ordering').
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 (one parameter, no output schema, no annotations), the description is adequately complete. It covers the input, output, and usage context. Could be slightly more specific about multiple matches, but the '唯一命中' condition implies this.
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 100% description coverage for the query parameter. The description adds value by providing concrete examples ('深圳湾', '太古里', '北京') and clarifying that the query can be a store name, mall, or city.
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?
Clearly states the tool finds stores by name, mall, or city, and returns storeId and status, with business hours on unique match. Distinct from siblings (get_menu, get_item_detail, preview_order) which serve later ordering steps.
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 says '点单第一步先找店' (first step of ordering is to find the store), establishing the tool as the entry point. Could more explicitly state when not to use, but the context and sibling list make the guidance clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
看商品点单详情：规格（SKU）、做法（温度/糖度等）、加料、是否估清。goodsId 从 get_menu 结果里取。
| Name | Required | Description | Default |
|---|---|---|---|
| goodsId | Yes | 商品 ID（get_menu 返回的 goodsId） | |
| storeId | Yes | 门店 ID（先用 find_store 查；如深圳湾万象城=503542） |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations; description lists data fields but does not mention side effects, read-only nature, authentication needs, or rate limits. Assumed safe read but not stated.
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 packs key information efficiently. Front-loaded with purpose and details, 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?
Adequate for a simple retrieval tool with good parameter descriptions, but lacks output format and any limitations or prerequisites beyond sibling hint.
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 covers 100% of parameters with descriptions. Description does not add new semantic meaning beyond what schema provides, so baseline 3 is appropriate.
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 retrieves order details (specifications, preparation, add-ons, sold-out status) and links to get_menu via goodsId. Distinguishes from siblings like get_menu and preview_order.
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?
Implied usage from mentioning goodsId from get_menu, but no explicit when-to-use or when-not-to-use compared to alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
组单算预估总价（本地累加；实际金额以门店收银台/订单为准）。同组做法（如温度）只能选一个，估清商品会拦截。
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | ||
| storeId | Yes | 门店 ID（先用 find_store 查；如深圳湾万象城=503542） |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses important behaviors: local accumulation (not final), actual amounts may differ, constraints on practices, and blocking of sold-out items. Since no annotations are provided, the description carries full burden and does so adequately.
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 two sentences, front-loads the core purpose, and each sentence adds 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?
For a tool with two parameters and no output schema, the description covers purpose, constraints, and estimation nature. It is complete enough for an agent to understand usage and limitations.
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 50%, and the description adds some context (e.g., practices constraint) but does not significantly expand on the schema's parameter descriptions. Baseline 3 is appropriate.
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 calculates an estimated total price for an order ('算预估总价'), specifies local accumulation, and distinguishes from siblings by focusing on price calculation rather than store or item lookups.
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 implicitly indicates when to use (for total preview) and provides constraints (same group practices only one, sold-out items block). However, it does not explicitly state when not to use or list alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose: finding stores, getting menu, item details, and order preview. No overlap.
All tool names follow a consistent verb_noun pattern in snake_case (find_store, get_menu, get_item_detail, preview_order).
4 tools is well-scoped for a tea ordering server, covering the core workflow without unnecessary complexity.
The tools cover the full user journey from finding a store to previewing an order with item details, leaving no dead ends for its stated purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for AI dialogue using various LLM models via AceDataCloud
Hosted MCP server for live public-data APIs and Skills for AI agents.
Hosted MCP for e-commerce: live product catalog, stock, and pricing for AI agents.
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/lichadecha/licha-order-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
