de en es ja ko ru zh

mcp-lad-lviv-ua

Name: mcp-lad-lviv-ua
Author: vbhjckfd

by vbhjckfd

Overview Schema Source Related Servers Discussions Admin

TypeScript

Hybrid

Timetable API Node

Node.js License: WTFPL MCP Registry

基于 Express 的利沃夫交通时刻表数据 API，带有只读 MCP 端点。

vbhjckfd/timetable-api-node MCP server

timetable-api-node MCP server

要求

Node.js 22 (参见 .nvmrc)

Related MCP server: GTFOBins MCP Server

本地运行

nvm use
make start

测试

nvm use && make test

MCP 服务器

此服务通过 Streamable HTTP 公开一个只读的 MCP 端点。

MCP 端点: /mcp
服务器卡片: /.well-known/mcp/server-card.json
发现提示: /robots.txt (非标准注释提示)

生产环境部署（参见 cloudbuild.yaml 以了解 Cloud Run）通过 api.lad.lviv.ua 提供 REST 和 MCP 服务。主站点 lad.lviv.ua 是公共交通网站（此仓库在 HTML 网站地图和表格中仍链接至该处，供用户查看，而非作为 API 主机）。在本地运行时请使用您自己的源。

LLM 和 `/mcp` 流程

MCP 客户端（Claude、Cursor 或 MCP SDK）通过 Streamable HTTP 以 JSON-RPC 方式与 POST /mcp 通信。工具处理程序复用与 REST API 相同的 Express 操作，并由 LokiJS 时刻表数据、GTFS SQLite（通过 gtfs）以及 实时 GTFS-RT 馈送（例如 track.ua-gis.com）提供支持。

graph LR;
  Client[LLM or MCP client] -->|JSON-RPC Streamable HTTP| Mcp["POST /mcp"];
  Mcp --> Tools[Tool handlers];
  Tools --> Actions[Express actions];
  Actions --> Loki[(LokiJS)];
  Actions --> Gtfs[(GTFS SQLite)];
  Actions --> Rt[GTFS-RT upstream];
  Loki --> Actions;
  Gtfs --> Actions;
  Rt --> Actions;
  Actions --> Tools;
  Tools --> Mcp;
  Mcp -->|MCP tool result| Client;

尝试实时 API

MCP server card REST stops.json REST routes.json

MCP Inspector (本地): 运行 npx @modelcontextprotocol/inspector，然后打开预填了传输方式和服务器 URL 的 UI（来自 inspector README）：

http://localhost:6274/?transport=streamable-http&serverUrl=https%3A%2F%2Fapi.lad.lviv.ua%2Fmcp

使用 Content-Type: application/json 发送 POST https://api.lad.lviv.ua/mcp。Streamable HTTP 传输可能需要 MCP 客户端自动设置的额外标头；如需进行快速手动测试，请遵循 MCP SDK 使用的相同序列（会话 initialize，然后是 tools/call）。示例 tools/call 正文格式：

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_stop_realtime",
    "arguments": { "stop_id": 101 }
  }
}

成功的工具响应会在 MCP content 项（type: "text"）中返回 字符串化的 JSON，且每个有效载荷都遵循严格的 UI 契约：

{
  "view": "transit_realtime",
  "data": { "...": "tool-specific source data" },
  "ui_blocks": [
    { "type": "map", "data": { "...": "map renderer input" } },
    { "type": "arrival_list", "data": { "...": "arrival list renderer input" } }
  ]
}

一致性规则：地图上渲染的每辆车必须在列表数据中具有匹配的 ETA，或者 eta_status: "unassigned"。

公开的工具

get_stop_realtime
get_route_static
get_route_realtime
get_stop_geometry
get_stops_around_location

参数 (JSON):

字段	类型	必需
`stop_id`	正整数或纯数字字符串	是

示例结果 (仅形状；值来自上游):

{
  "view": "transit_realtime",
  "data": {
    "stop": { "id": "707", "name": "Стадіон Сільмаш", "lat": 49.84, "lng": 24.03 },
    "arrivals": [
      {
        "route": "T30",
        "direction": "Рясівська",
        "vehicle_type": "tram",
        "arrival_minutes": 4,
        "vehicle_id": "tram_123",
        "lat": 49.83,
        "lng": 24.02,
        "bearing": 120
      }
    ],
    "updated_at": "2026-01-23T12:00:00Z"
  },
  "ui_blocks": [
    {
      "type": "map",
      "data": { "center": [49.84, 24.03], "vehicles": [] }
    },
    {
      "type": "arrival_list",
      "data": { "arrivals": [] }
    }
  ]
}

参数 (JSON):

字段	类型	必需
`route_name`	路线简称 (例如 `"T30"`, `"32A"`) 或数字外部 ID	是

示例结果 (仅形状；为简洁起见截断了站点):

{
  "view": "transit_realtime",
  "data": {
    "route": {
      "name": "T30",
      "long_name": "Рясне-2 — Сихів",
      "color": "#e81717",
      "type": "tram"
    },
    "stops": [
      [
        { "id": "101", "name": "Головний вокзал", "lat": 49.841, "lng": 24.003, "departures": ["05:30", "05:52"] },
        { "id": "707", "name": "Стадіон Сільмаш", "lat": 49.838, "lng": 24.021, "departures": [] }
      ],
      [
        { "id": "707", "name": "Стадіон Сільмаш", "lat": 49.838, "lng": 24.021, "departures": [] },
        { "id": "101", "name": "Головний вокзал", "lat": 49.841, "lng": 24.003, "departures": [] }
      ]
    ],
    "shapes": [
      [[49.841, 24.003], [49.839, 24.012], [49.838, 24.021]],
      [[49.838, 24.021], [49.839, 24.012], [49.841, 24.003]]
    ],
    "updated_at": "2026-01-23T12:00:00Z"
  },
  "ui_blocks": [
    {
      "type": "map",
      "data": {
        "center": [49.841, 24.003],
        "zoom": 13,
        "polylines": [[[49.841, 24.003], [49.839, 24.012], [49.838, 24.021]]],
        "stops": [
          { "id": "101", "name": "Головний вокзал", "lat": 49.841, "lng": 24.003 },
          { "id": "707", "name": "Стадіон Сільмаш", "lat": 49.838, "lng": 24.021 }
        ],
        "vehicles": []
      }
    }
  ]
}

stops[0] 是方向 0（去程），stops[1] 是方向 1（回程）。departures 仅针对方向 0 填充。shapes 遵循相同的双元素顺序。地图块使用方向 0 的折线和所有唯一站点作为标记。

参数 (JSON):

字段	类型	必需
`route_name`	路线简称 (例如 `"T30"`, `"32A"`) 或数字外部 ID	是

示例结果:

{
  "view": "transit_realtime",
  "data": {
    "route_name": "T30",
    "vehicles": [
      {
        "id": "tram_123",
        "direction": 0,
        "lat": 49.838,
        "lng": 24.021,
        "bearing": 120,
        "lowfloor": true
      }
    ],
    "updated_at": "2026-01-23T12:00:00Z"
  },
  "ui_blocks": [
    {
      "type": "map",
      "data": {
        "center": [49.838, 24.021],
        "zoom": 13,
        "vehicles": [
          {
            "id": "tram_123",
            "direction": 0,
            "lat": 49.838,
            "lng": 24.021,
            "bearing": 120,
            "lowfloor": true
          }
        ]
      }
    }
  ]
}

direction 与 get_route_static 的 stops 数组索引匹配（0 = 去程，1 = 回程）。lowfloor: true 表示低地板车辆。当路线上当前没有车辆运行时，返回空的 vehicles 数组。

参数:

字段	类型	必需
`stop_id`	正整数或纯数字字符串	是

示例结果:

{
  "view": "transit_realtime",
  "data": {
    "stop": { "id": "707", "name": "Стадіон Сільмаш", "lat": 49.84, "lng": 24.03 },
    "routes": [
      {
        "route": "T30",
        "polyline": [[49.84, 24.03], [49.83, 24.02]]
      }
    ]
  },
  "ui_blocks": [{ "type": "map", "data": { "routes": [] } }]
}

返回地图点附近的站点（数字代码、名称、坐标、距离）。旨在供渲染 map UI 块的主机使用（例如 ChatGPT）：一个包含 多个站点标记 和搜索中心的块。使用与 GET /closest 相同的后端（见下文）。

参数 (JSON):

字段	类型	必需
`latitude`	数字, −90…90	是
`longitude`	数字, −180…180	是
`radius_meters`	整数, 50…3000	否 (默认 1000)

示例结果 (仅形状):

{
  "view": "transit_realtime",
  "data": {
    "center_lat": 49.84,
    "center_lng": 24.03,
    "radius_meters": 1000,
    "stops": [
      {
        "id": "707",
        "name": "Стадіон Сільмаш",
        "lat": 49.841,
        "lng": 24.031,
        "distance_meters": 120
      }
    ],
    "updated_at": "2026-01-23T12:00:00Z"
  },
  "ui_blocks": [
    {
      "type": "map",
      "data": {
        "center": [49.84, 24.03],
        "zoom": 15,
        "stops": [
          {
            "id": "707",
            "name": "Стадіон Сільмаш",
            "lat": 49.841,
            "lng": 24.031,
            "distance_meters": 120
          }
        ],
        "vehicles": []
      }
    }
  ]
}

半径 ≤ 1500 米时地图缩放级别为 15，半径较大时（最高 3000 米）为 14。

安全模型

公共只读（无身份验证）。
不公开任何变更工具。
robots.txt 仅作为尽力而为的发现提示，而非协议契约。

REST API

所有端点均返回 JSON。:code 是数字站点代码；:name 是路线简称（例如 T1, 32A）或数字外部 ID。

站点

`GET /stops.json`

所有站点作为 JSON 数组，按代码排序。

响应: { code, name, eng_name, location: [lat, lng], routes, sign, sign_pdf } 数组。

(GET /stops 返回 HTML 表格。)

`GET /stops/:code`

带有实时时刻表的单个站点。短缓存（5–10 秒）。

可选: skipTimetableData=1 — 省略实时到达信息（长缓存响应）。
响应: { code, name, eng_name, latitude, longitude, transfers, timetable }。

`GET /stops/:code/timetable`

仅站点的实时时刻表。短缓存（5–10 秒）。

响应: 时刻表项数组。

`GET /stops/:code/static`

无实时数据的静态站点信息。长缓存（30 天）。

响应: { code, name, eng_name, latitude, longitude, transfers }。

`GET /closest?latitude={lat}&longitude={lng}`

附近的站点 — 与 get_stops_around_location 相同的搜索，适用于非 MCP 客户端。

可选: radius — 米，限制在 50 到 3000 之间（默认 1000）。
响应: { code, name, latitude, longitude, distance_meters } 的 JSON 数组（按距离排序）。

路线

`GET /routes.json`

所有路线作为 JSON 数组，按简称排序。

响应: 来自时刻表存储的原始路线对象。

(GET /routes 返回 HTML 表格。)

`GET /routes/static/:name`

路线形状、站点列表和元数据。长缓存（30 天）。

响应: { id, color, type, route_short_name, route_long_name, stops: [[dir0…], [dir1…]], shapes }。

`GET /routes/dynamic/:name`

路线的实时车辆位置。短缓存（10 秒）。

响应: { id, direction, location: [lat, lng], bearing, lowfloor } 数组。

车辆

`GET /vehicle/:vehicleId`

单辆车的实时位置和即将到达的站点。短缓存（5 秒）。

响应: { location: [lat, lng], routeId, bearing, direction, licensePlate, arrivals }。

`GET /transport?latitude={lat}&longitude={lng}`

点位 1 公里范围内的车辆。短缓存（10 秒）。

响应: { id, route, vehicle_type, color, location: [lat, lng], bearing, lowfloor } 数组。

Available Tools

5 tools

get_route_realtimeGet Route RealtimeA

Read-onlyIdempotent

Inspect

Returns live positions for all vehicles currently running on a route, optimised for map rendering. Use when the user asks "where is my tram/bus right now?" or wants to see all active vehicles on a specific route on a map. Prefer get_stop_realtime when the user is at a stop and wants to know arrival times rather than vehicle positions. Prefer get_route_static when only the route shape or stop list is needed without live data. Requires a route short name (e.g. "T30", "32A") or numeric external ID.

ParametersJSON Schema

Name	Required	Description	Default
`route_name`	Yes	Route short name (e.g. "T30", "32A") or numeric external ID.

Output Schema

ParametersJSON Schema

Name	Required	Description
`data`	Yes
`view`	Yes
`ui_blocks`	Yes

TDQS

A4.8/5.0

Behavior4/5

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, openWorldHint=false. Description adds real-time and map rendering context, consistent with annotations. No contradictions, but could mention possible data latency or frequency of updates.

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 a note, all valuable. Front-loaded with the main action, then usage guidelines and input format. No wasted words.

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

Completeness5/5

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

Given that an output schema exists, the description does not need to explain return values. It covers what the tool does, when to use it, and input requirements. Fully sufficient for an agent to decide to invoke.

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

Parameters5/5

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

Only one parameter 'route_name' with 100% schema coverage. Description adds examples ('T30', '32A') and clarifies it accepts short name or numeric external ID, providing more meaning than the schema alone.

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 clearly states it returns live positions for all vehicles on a route, optimized for map rendering. It distinguishes from siblings by specifying use cases like 'where is my tram/bus right now?' versus arrival times at a stop.

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

Usage Guidelines5/5

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

Explicitly says when to use this tool vs alternatives: prefer get_stop_realtime for arrival times, get_route_static for route shape/stop list without live data. Also specifies input format requirement (route short name or numeric external ID).

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

get_route_staticGet Route StaticA

Read-onlyIdempotent

Inspect

Returns static route metadata: short and long name, vehicle type, brand colour, ordered stop lists for both directions, and route polylines (shapes) for map rendering. Use when the user asks which stops a route serves, what a route looks like on a map, or what the scheduled departure times are. Do NOT use this when live vehicle positions are needed — use get_route_realtime instead. Requires a route short name (e.g. "T30", "32A") or numeric external ID; call get_stops_around_location first if you only know a location and need to discover which routes serve it.

ParametersJSON Schema

Name	Required	Description	Default
`route_name`	Yes	Route short name (e.g. "T30", "32A") or numeric external ID.

Output Schema

ParametersJSON Schema

Name	Required	Description
`data`	Yes
`view`	Yes
`ui_blocks`	Yes

TDQS

A4.7/5.0

Behavior4/5

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

Annotations (readOnlyHint, idempotentHint) already indicate safety. Description adds context that data is static and what it includes, but doesn't disclose any hidden behaviors. No contradictions.

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?

Every sentence is purposeful. Front-loaded with purpose, then usage guidelines, then parameter notes. No redundancy.

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

Completeness5/5

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

For a static data retrieval tool with an output schema (not shown) and sibling tools listed, the description covers all necessary context: what, when, when not, and how to get inputs. Complete.

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

Parameters4/5

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

Schema coverage is 100% and the parameter description is clear. Description adds value by explaining how to obtain the route name if needed (via get_stops_around_location), which aids tool selection.

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 'Returns' and lists concrete resources: static route metadata, stop lists, polylines. It distinguishes from siblings by explicitly mentioning when not to use (live positions -> get_route_realtime).

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

Usage Guidelines5/5

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

Provides explicit use cases (user asks for stops, map, scheduled times) and non-use cases (live positions) with alternative named. Also gives prerequisite for obtaining route name if unknown.

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

get_stop_geometryGet Stop GeometryA

Read-onlyIdempotent

Inspect

Returns static map context for a stop: its marker and polylines for every route that serves it. No live data is fetched. Use this when you need to enrich an existing map with route shapes (e.g. overlay polylines alongside a get_stop_realtime map block) or when the user asks to visualise which routes pass a stop without needing live arrivals. Do NOT use this when live arrival times or vehicle positions are needed — use get_stop_realtime instead. Requires a numeric stop ID; call get_stops_around_location first if you only have coordinates.

ParametersJSON Schema

Name	Required	Description	Default
`stop_id`	Yes	Municipal stop code shown on stop signage (e.g. 707). Accepts a positive integer or an equivalent digit-only string.

Output Schema

ParametersJSON Schema

Name	Required	Description
`data`	Yes
`view`	Yes
`ui_blocks`	Yes

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint. The description adds that no live data is fetched and specifies return components (marker, polylines), which is valuable beyond annotations.

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 well-structured sentences, front-loaded, no wasted words. Every sentence adds value.

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

Completeness5/5

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

Given the tool has an output schema, the description adequately covers purpose, usage guidelines, and prerequisites. Parameter is simple. No gaps identified.

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 coverage is 100% with clear parameter description. The description reiterates it requires a numeric stop ID and adds cross-reference to get_stops_around_location, but adds minimal new semantic info beyond the schema.

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 clearly states the tool returns static map context for a stop: marker and polylines for every route. It uses specific verbs and resource, distinguishing from sibling get_stop_realtime.

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

Usage Guidelines5/5

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

Explicitly says when to use (enrich map, visualize routes) and when not to (live data needed), with a direct reference to get_stop_realtime as alternative. Also provides prerequisite to call get_stops_around_location if only coordinates are available.

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

get_stop_realtimeGet Stop RealtimeA

Read-onlyIdempotent

Inspect

Returns live arrivals and vehicle positions for a stop, producing both a map UI block and a structured arrival list. Use this as the default tool when the user asks about arrivals, departures, or vehicles at a specific stop. Prefer get_stop_geometry when only static route polylines are needed and live data is irrelevant. Requires a numeric stop ID (shown on stop signage); use get_stops_around_location first if you only have an address or coordinates.

ParametersJSON Schema

Name	Required	Description	Default
`stop_id`	Yes	Municipal stop code shown on stop signage (e.g. 707). Accepts a positive integer or an equivalent digit-only string.

Output Schema

ParametersJSON Schema

Name	Required	Description
`data`	Yes
`view`	Yes
`ui_blocks`	Yes

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already indicate read-only and idempotent. The description adds that it produces a map UI block and structured list, which is behavioral context beyond annotations. No contradictions.

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 with essential information, front-loaded with purpose, and no extraneous words. Every sentence earns its place.

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

Completeness5/5

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

For a tool with one parameter, full schema coverage, and output schema, the description covers all necessary aspects: functionality, usage context, parameter source, and sibling relationships.

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

Parameters4/5

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

Schema coverage is 100%, so baseline 3. The description adds value by explaining how to obtain the stop ID (from signage) and when to use a different tool for other inputs, exceeding mere schema details.

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 clearly states the tool returns live arrivals and vehicle positions for a stop, specifying both a map UI block and structured arrival list. It distinguishes itself from siblings like `get_stop_geometry` and `get_stops_around_location`.

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

Usage Guidelines5/5

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

Explicitly says to use as default for arrivals/departures, prefers `get_stop_geometry` for static data, and suggests `get_stops_around_location` for address/coordinate inputs. Provides clear when-to-use and alternatives.

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

get_stops_around_locationGet Stops Around LocationA

Read-onlyIdempotent

Inspect

Discovers transit stops near a geographic point, returning each stop's numeric code, name, coordinates, and walking distance. Also emits a map UI block with multiple markers for map-capable clients (e.g. ChatGPT). Use this as the first step whenever the user provides an address, place name, or coordinates and you need stop IDs before calling get_stop_realtime or get_stop_geometry. Do NOT use this to fetch arrivals or live vehicle data — it returns stop metadata only. Default radius is 1 000 m; narrow it (e.g. 300 m) for dense urban areas or widen it (up to 3 000 m) for rural locations.

ParametersJSON Schema

Name	Required	Description
`latitude`	Yes	Decimal latitude of the search centre, WGS84 (e.g. 49.842 for central Lviv).
`longitude`	Yes	Decimal longitude of the search centre, WGS84 (e.g. 24.031 for central Lviv).
`radius_meters`	No	Search radius in metres (50–3000, default 1000). Use ~300 for dense urban intersections, up to 3000 for suburban or rural areas.

Output Schema

ParametersJSON Schema

Name	Required	Description
`data`	Yes
`view`	Yes
`ui_blocks`	Yes

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so safety profile is clear. Description adds valuable context: emits a map UI block for map-capable clients, default radius is 1000 m, and valid radius range (50–3000). This goes beyond annotations without contradicting them.

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?

Description is efficiently structured: first sentence states primary function and added map UI block, second sentence provides usage guidance and exclusions, third sentence offers radius optimization tips. No redundant or superfluous information; every sentence earns its place.

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

Completeness5/5

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

Given that an output schema exists (so return structure need not be described), the description is complete: it covers purpose, when to use, when not to use, and parameter behavior. Context signals (3 params, 2 required, 100% schema coverage, sibling tools) are fully addressed by the description.

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

Parameters4/5

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

Input schema already covers all parameters with descriptions (100% coverage). Description adds no new parameter details but provides usage context: default radius (1000 m), suggested values for dense urban (300 m) vs rural (3000 m), and clarifies that latitude/longitude use WGS84. This added value justifies a score above baseline 3.

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?

Description clearly states the tool discovers transit stops near a geographic point, returning specific metadata (code, name, coordinates, distance) and a map UI block. It distinguishes itself from sibling tools like get_stop_realtime (arrivals) and get_stop_geometry (geometry), ensuring unambiguous purpose.

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

Usage Guidelines5/5

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

Explicitly says to use as the first step when needing stop IDs before calling get_stop_realtime or get_stop_geometry, and warns not to use for arrivals or live data. Also provides radius adjustment guidance for dense urban vs rural areas, leaving no ambiguity about when to employ this tool.

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.

5 tool updatesv1.0.11May 10, 2026
- Addedget_route_realtime
- Addedget_route_static
- Addedget_stop_geometry
- Addedget_stop_realtime
- Addedget_stops_around_location
5 tool updatesv1.0.9Apr 30, 2026
- Removedget_route_realtime
- Removedget_route_static
- Removedget_stop_geometry
- Removedget_stop_realtime
- Removedget_stops_around_location

3 tool updatesv1.0.8Apr 29, 2026

Changedget_stop_geometry2 fields changed

changedInput schema / properties / stop_id / anyOf

Previous value: -[
-  {
-    "description": "Numeric municipal stop code (e.g. 707).",
-    "exclusiveMinimum": 0,
-    "maximum": 9007199254740991,
-    "type": "integer"
-  },
-  {
-    "description": "Municipal stop code as digits-only string (e.g. \"707\").",
-    "pattern": "^\\d+$",
-    "type": "string"
-  }
-]New value: +[
+  {
+    "description": "Positive integer stop code (e.g. 707).",
+    "exclusiveMinimum": 0,
+    "maximum": 9007199254740991,
+    "type": "integer"
+  },
+  {
+    "description": "Stop code as a digits-only string (e.g. \"707\").",
+    "pattern": "^\\d+$",
+    "type": "string"
+  }
+]

addedInput schema / properties / stop_id / description

Added value: +"Municipal stop code shown on stop signage (e.g. 707). Accepts a positive integer or an equivalent digit-only string."

Changedget_stop_realtime2 fields changed

changedInput schema / properties / stop_id / anyOf

Previous value: -[
-  {
-    "description": "Numeric municipal stop code (e.g. 707).",
-    "exclusiveMinimum": 0,
-    "maximum": 9007199254740991,
-    "type": "integer"
-  },
-  {
-    "description": "Municipal stop code as digits-only string (e.g. \"707\").",
-    "pattern": "^\\d+$",
-    "type": "string"
-  }
-]New value: +[
+  {
+    "description": "Positive integer stop code (e.g. 707).",
+    "exclusiveMinimum": 0,
+    "maximum": 9007199254740991,
+    "type": "integer"
+  },
+  {
+    "description": "Stop code as a digits-only string (e.g. \"707\").",
+    "pattern": "^\\d+$",
+    "type": "string"
+  }
+]

addedInput schema / properties / stop_id / description

Added value: +"Municipal stop code shown on stop signage (e.g. 707). Accepts a positive integer or an equivalent digit-only string."

Changedget_stops_around_location3 fields changed

changedInput schema / properties / latitude / description

Previous value: -"Center latitude (WGS84)."New value: +"Decimal latitude of the search centre, WGS84 (e.g. 49.842 for central Lviv)."

changedInput schema / properties / longitude / description

Previous value: -"Center longitude (WGS84)."New value: +"Decimal longitude of the search centre, WGS84 (e.g. 24.031 for central Lviv)."

changedInput schema / properties / radius_meters / description

Previous value: -"Search radius in meters (default 1000; same cap as the public /closest API)."New value: +"Search radius in metres (50–3000, default 1000). Use ~300 for dense urban intersections, up to 3000 for suburban or rural areas."

2 tool updatesv1.0.5Apr 29, 2026
- Addedget_route_realtime
- Addedget_route_static
1 tool updatev1.0.4Apr 29, 2026
- Removedget_vehicles_by_stop
4 tool updatesv1.0.0Apr 29, 2026
- First observedget_stop_geometry
- First observedget_stop_realtime
- First observedget_stops_around_location
- First observedget_vehicles_by_stop

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

A4.9/5.0

Scored 2026-06-04 03:45 across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: route static vs realtime, stop geometry vs realtime, and stop discovery. Descriptions explicitly disambiguate when to use each, leaving no ambiguity.

Naming Consistency5/5

All tool names follow the consistent pattern 'get_[resource]_[modifier]' in snake_case, e.g., get_route_realtime, get_stop_geometry. The naming is predictable and easy to understand.

Tool Count5/5

5 tools is well-scoped for a transit information server, covering all essential operations: route static and realtime data, stop static geometry and realtime arrivals, and stop discovery. No excess or deficiency.

Completeness5/5

The tool surface is complete for the domain: users can discover stops, get realtime arrivals, static route info, route shapes, and live vehicle positions. There are no obvious gaps such as missing CRUD operations or dead ends.

Maintenance

ActivityActive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

Live Times Transit
io.github.travelwhiz-ltd
Read-only public transit departures, stop search, and city coverage for bus and train users.
Travel & Transportation Location Services
1
Mbta A
io.github.pipeworx-io
MBTA MCP — Boston real-time transit via the MBTA v3 API (api-v3.mbta.com)
Travel & Transportation Location Services
402
Transit Land A
io.github.pipeworx-io
Transitland MCP — global GTFS aggregator
Travel & Transportation Open Data
452
Septa A
io.github.pipeworx-io
SEPTA MCP — Philadelphia SEPTA real-time transit (www3.septa.org/api, keyless)
Travel & Transportation Open Data
2

Related MCP Servers

Caltrain MCP Server
Travel & Transportation Agent Orchestration
davidyen1124
F
license
A
quality
A
maintenance
A Model Context Protocol server that provides real-time Caltrain schedule information, allowing AI assistants to look up train departures between any stations and access station information using GTFS data.
Updated 16 days ago (2026-09-27 18:06 UTC)
2
10
-
GTFOBins MCP Server
evilbotnet
F
license
Not graded
quality
D
maintenance
A server that provides seamless access to the GTFOBins database through Claude Desktop, allowing users to query exploitation techniques, search for specific binaries, and explore privilege escalation methods directly from Claude conversations.
Updated a year ago (2025-07-21 01:42 UTC)
-
Auckland Transport MCP Server
Travel & Transportation Location Services Open Data
airatech
A
license
Not graded
quality
D
maintenance
Enables searching for Auckland public transport stops and retrieving real-time transit schedules and timetables using the Auckland Transport API with GTFS standardized data.
Updated 10 months ago (2025-12-07 09:26 UTC)
MIT
OC Transpo MCP Server
Travel & Transportation Location Services Open Data
dwdraju
F
license
Not graded
quality
D
maintenance
Provides real-time transit data for OC Transpo in Ottawa, including live vehicle positions and trip updates via GTFS-RT feeds. It enables AI agents to monitor arrival delays, schedule changes, and transit telemetry through the Model Context Protocol.
Updated 8 months ago (2026-02-23 02:05 UTC)
2
-

Timetable API Node

要求

本地运行

测试

MCP 服务器

LLM 和 /mcp 流程

尝试实时 API

公开的工具

安全模型

REST API

站点

GET /stops.json

GET /stops/:code

GET /stops/:code/timetable

GET /stops/:code/static

GET /closest?latitude={lat}&longitude={lng}

路线

GET /routes.json

GET /routes/static/:name

GET /routes/dynamic/:name

车辆

GET /vehicle/:vehicleId

GET /transport?latitude={lat}&longitude={lng}

Available Tools

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

LLM 和 `/mcp` 流程

`GET /stops.json`

`GET /stops/:code`

`GET /stops/:code/timetable`

`GET /stops/:code/static`

`GET /closest?latitude={lat}&longitude={lng}`

`GET /routes.json`

`GET /routes/static/:name`

`GET /routes/dynamic/:name`

`GET /vehicle/:vehicleId`

`GET /transport?latitude={lat}&longitude={lng}`