Skip to main content
Glama
enesjakozh
kennyckk

KMB Bus MCP Server

by kennyckk
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

九巴巴士MCP服务器

一个模型上下文协议 (MCP) 服务器，可实时访问香港九龙巴士 (KMB) 和龙运巴士 (Long Win Bus) 的路线信息和到达时间。该服务器支持语言模型查询香港公交服务信息，以解答用户关于公交路线、站点和预计到达时间的问题。

特征

  • 实时公交车到站信息（ETA）

  • 综合公交线路查询

  • 公交车站信息和搜索

  • 路线站点映射

  • 缓存系统优化 API 调用

  • 双语支持（英语和繁体中文）

Related MCP server: Hong Kong Transportation MCP Server

数据源

该项目利用 KMB/LWB 官方开放数据 API：

先决条件

  • Python 3.10 或更高版本

  • uv 包管理器

安装

  1. 首先，如果尚未安装 uv，请安装它：

curl -LsSf https://astral.sh/uv/install.sh | sh

  1. 克隆存储库：

git clone git@github.com:kennyckk/mcp_hkbus.git
cd mcp_hkbus

  1. 使用uv处理python包：

uv sync #using uv.lock

用法

  1. 在您的 MCP 客户端（例如 Claude Desktop）中编辑配置：

{
  "mcpServers": {
    "bus_service": {
      "command": "path/to/uv.exe",
      "args": ["--directory", "path/to/kmb_bus", "run", "kmb_mcp.py"],
      "background": true
    }
  }
}

  1. 服务器提供了几种可供语言模型用来查询公交车信息的工具：

  • get_route_list() ：获取所有公交路线列表

  • get_stop_list() ：获取所有公交车站列表

  • get_route_stops() ：获取特定路线的站点

  • find_stops_by_name() ：按名称搜索公交车站

  • get_all_routes_at_stop() ：获取服务特定站点的所有路线

  • get_eta() ：获取预计到达时间

测试

使用 pytest 运行测试套件：

pytest test/kmb-mcp-tests.py

依赖项

  • httpx ：用于异步 HTTP 请求

  • fastmcp ：用于 MCP 服务器实现

  • pytest ：用于测试（仅限开发）

贡献

欢迎贡献代码！欢迎提交 Pull 请求。

致谢

  • 九巴/龙运巴士提供开放数据API

  • MCP 协议开发者

笔记

此服务依赖于 KMB/LWB 开放数据 API。请注意 API 的速率限制，并在生产环境中实施适当的错误处理。

Available Tools

5 tools
find_buses_to_destinationB

Find bus routes that go to a specified destination.

Args:
    destination: The destination to search for (e.g., "Central", "Mong Kok", "Airport")
ParametersJSON Schema
NameRequiredDescriptionDefault
destinationYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.1/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the action ('Find bus routes') but lacks details on traits like response format, pagination, rate limits, error conditions, or whether it's a read-only operation. This is a significant gap for a tool with no annotation coverage.

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

Conciseness4/5

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

The description is appropriately sized and front-loaded, with the core purpose stated first followed by parameter details. The two sentences are efficient and focused, with no wasted words, though the structure is simple without explicit sections.

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

Completeness3/5

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

Given the tool's moderate complexity (1 parameter, no annotations, but with an output schema), the description is partially complete. It covers the purpose and parameter semantics adequately, but lacks behavioral context and usage guidelines. The presence of an output schema reduces the need to explain return values, but more guidance is still warranted.

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?

The description adds meaningful context beyond the input schema, which has 0% description coverage. It explains the 'destination' parameter with examples ('Central', 'Mong Kok', 'Airport'), clarifying the expected input format and scope. This compensates well for the schema's lack of documentation.

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

Purpose4/5

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

The description clearly states the tool's purpose with a specific verb ('Find') and resource ('bus routes'), and specifies the target ('to a specified destination'). It doesn't explicitly differentiate from sibling tools like 'get_all_routes_at_stop' or 'get_route_stops_info', but the destination-focused search is reasonably distinct.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'find_stop_by_name' or 'get_all_routes_at_stop', nor does it specify prerequisites or exclusions (e.g., whether it requires real-time data or works with schedules only).

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

find_stop_by_nameA

Find bus stops matching a name or partial name.

Args:
    stop_name: Full or partial name of the bus stop to search for
ParametersJSON Schema
NameRequiredDescriptionDefault
stop_nameYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes a search operation but lacks details on permissions, rate limits, pagination, or return format. The description does not contradict annotations, but it provides minimal behavioral context beyond the basic operation, which is insufficient for a tool with no annotation coverage.

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

Conciseness5/5

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

The description is appropriately sized and front-loaded, with the first sentence stating the tool's purpose clearly. The second sentence provides essential parameter details without redundancy. Every sentence earns its place, making it efficient and well-structured.

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

Completeness4/5

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

Given the tool's low complexity (1 parameter) and the presence of an output schema (which handles return values), the description is largely complete. It covers purpose and parameter semantics adequately. However, the lack of behavioral details (e.g., search behavior, limitations) and usage guidelines slightly reduces completeness, though the output schema mitigates some gaps.

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?

The description adds significant meaning beyond the input schema, which has 0% description coverage. It explicitly explains that 'stop_name' is for 'Full or partial name of the bus stop to search for', clarifying the parameter's purpose and usage, which compensates fully for the schema's lack of documentation.

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's purpose with a specific verb ('Find') and resource ('bus stops'), specifying it matches by 'name or partial name'. It distinguishes from siblings like 'get_all_routes_at_stop' (which focuses on routes) and 'find_buses_to_destination' (which focuses on buses), making it highly specific and differentiated.

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

Usage Guidelines3/5

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

The description implies usage for searching bus stops by name, but does not explicitly state when to use this tool versus alternatives like 'get_route_stops_info' (which might provide stop details within a route context) or 'get_all_routes_at_stop' (which focuses on routes at a specific stop). No exclusions or prerequisites are mentioned, leaving usage context somewhat inferred.

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

get_all_routes_at_stopB

Get all bus routes that pass through a specified bus stop.

Args:
    stop_name: Name of the bus stop
ParametersJSON Schema
NameRequiredDescriptionDefault
stop_nameYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.4/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure but offers minimal information. It states what the tool does but doesn't describe response format, error handling, rate limits, or whether it requires authentication. For a read operation with no annotation coverage, this leaves significant gaps in understanding how the tool behaves.

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

Conciseness4/5

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

The description is appropriately sized with two sentences: one stating the purpose and another documenting the parameter. It's front-loaded with the core functionality, though the parameter documentation could be integrated more seamlessly rather than as a separate 'Args' section.

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

Completeness3/5

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

Given the tool's low complexity (one parameter) and the presence of an output schema (which handles return values), the description is minimally adequate. However, with no annotations and incomplete behavioral transparency, it doesn't fully prepare an agent for edge cases or system constraints, leaving room for improvement in completeness.

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?

The description adds meaningful context for the single parameter 'stop_name' by explaining it's 'Name of the bus stop', which clarifies its purpose beyond the schema's basic title. With 0% schema description coverage and only one parameter, this adequately compensates, though it doesn't detail format constraints (e.g., case sensitivity).

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 specific action ('Get all bus routes') and resource ('that pass through a specified bus stop'), making the purpose immediately understandable. It distinguishes from sibling tools like 'find_stop_by_name' (which finds stops) and 'get_next_bus' (which provides timing information) by focusing on route enumeration 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 Guidelines2/5

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 like 'find_buses_to_destination' or 'get_route_stops_info'. It lacks context about prerequisites (e.g., whether the stop must exist in the system) or exclusions (e.g., not for real-time bus tracking).

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

get_next_busB

Get the next arrival time for a specified bus route at a stop.

Args:
    route: The bus route number (e.g., "1A", "6", "960")
    stop_name: The name of the bus stop
ParametersJSON Schema
NameRequiredDescriptionDefault
routeYes
stop_nameYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes what the tool does (retrieves arrival time) but lacks critical behavioral details: it doesn't specify if this requires real-time data access, whether results are cached, what happens if the route/stop doesn't exist, or if there are rate limits. For a tool with zero annotation coverage, this leaves significant gaps in understanding its operational behavior.

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

Conciseness5/5

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

The description is appropriately sized and front-loaded: the first sentence states the core purpose clearly, followed by a structured 'Args' section that efficiently documents parameters with examples. Every sentence earns its place without redundancy or fluff, making it easy for an agent to parse quickly.

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

Completeness3/5

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

Given the tool's moderate complexity (2 required parameters, no annotations, but with an output schema), the description is minimally adequate. It covers the basic purpose and parameters but lacks behavioral context (e.g., error handling, data freshness). The presence of an output schema means the description doesn't need to explain return values, but it should still address usage guidelines and operational traits to be more 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?

The description adds meaningful semantics beyond the input schema. The schema has 0% description coverage (only titles 'Route' and 'Stop Name'), but the description provides concrete examples for 'route' (e.g., '1A', '6', '960') and clarifies that 'stop_name' is the name of the bus stop. This compensates well for the low schema coverage, though it doesn't detail format constraints (e.g., case sensitivity).

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

Purpose4/5

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

The description clearly states the tool's purpose: 'Get the next arrival time for a specified bus route at a stop.' It includes a specific verb ('Get'), resource ('next arrival time'), and scope ('bus route at a stop'). However, it doesn't explicitly differentiate from sibling tools like 'get_all_routes_at_stop' or 'find_buses_to_destination', which prevents a perfect score.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'get_all_routes_at_stop' (which might list all routes at a stop) or 'find_buses_to_destination' (which might prioritize destination over route). Without any context on usage scenarios or exclusions, the agent must infer based on tool names alone.

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

get_route_stops_infoB

Get all stops along a specified bus route.

Args:
    route: The bus route number (e.g., "1A", "6", "960")
ParametersJSON Schema
NameRequiredDescriptionDefault
routeYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.3/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states what the tool does ('Get all stops') without mentioning any behavioral traits such as whether it's read-only, potential rate limits, error handling, or what the output contains. This is inadequate for a tool with no annotation coverage.

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

Conciseness4/5

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

The description is appropriately sized and front-loaded, with the core purpose stated clearly in the first sentence. The parameter explanation is concise and directly relevant. It could be slightly improved by integrating the parameter details more seamlessly, but it avoids unnecessary verbosity.

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

Completeness3/5

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

Given the tool's low complexity (1 parameter) and the presence of an output schema, the description is minimally adequate. However, it lacks context about behavioral aspects (e.g., read-only nature, error cases) and doesn't leverage sibling tool names to guide usage, leaving gaps in completeness despite the output schema handling return values.

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?

The description adds significant value beyond the input schema, which has 0% description coverage. It explains the 'route' parameter as 'The bus route number' and provides concrete examples (e.g., '1A', '6', '960'), clarifying the expected format and semantics that the schema alone does not cover.

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

Purpose4/5

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

The description clearly states the tool's purpose with a specific verb ('Get') and resource ('all stops along a specified bus route'), making it immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_all_routes_at_stop' or 'find_stop_by_name', which prevents a perfect score.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'get_all_routes_at_stop' (which might provide overlapping information) or clarify scenarios where this tool is preferred, leaving the agent to infer usage context.

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.

  1. 5 tool updatesv1.0.0
    • Changedfind_buses_to_destination1 field changed
      • changedOutput schema / (root)
        Previous value: -nullNew value: +{
+  "properties": {
+    "result": {
+      "title": "Result",
+      "type": "string"
+    }
+  },
+  "required": [
+    "result"
+  ],
+  "title": "find_buses_to_destinationOutput",
+  "type": "object"
+}
    • Changedfind_stop_by_name1 field changed
      • changedOutput schema / (root)
        Previous value: -nullNew value: +{
+  "properties": {
+    "result": {
+      "title": "Result",
+      "type": "string"
+    }
+  },
+  "required": [
+    "result"
+  ],
+  "title": "find_stop_by_nameOutput",
+  "type": "object"
+}
    • Changedget_all_routes_at_stop1 field changed
      • changedOutput schema / (root)
        Previous value: -nullNew value: +{
+  "properties": {
+    "result": {
+      "title": "Result",
+      "type": "string"
+    }
+  },
+  "required": [
+    "result"
+  ],
+  "title": "get_all_routes_at_stopOutput",
+  "type": "object"
+}
    • Changedget_next_bus1 field changed
      • changedOutput schema / (root)
        Previous value: -nullNew value: +{
+  "properties": {
+    "result": {
+      "title": "Result",
+      "type": "string"
+    }
+  },
+  "required": [
+    "result"
+  ],
+  "title": "get_next_busOutput",
+  "type": "object"
+}
    • Changedget_route_stops_info1 field changed
      • changedOutput schema / (root)
        Previous value: -nullNew value: +{
+  "properties": {
+    "result": {
+      "title": "Result",
+      "type": "string"
+    }
+  },
+  "required": [
+    "result"
+  ],
+  "title": "get_route_stops_infoOutput",
+  "type": "object"
+}
  2. 5 tool updates
    • First observedfind_buses_to_destination
    • First observedfind_stop_by_name
    • First observedget_all_routes_at_stop
    • First observedget_next_bus
    • First observedget_route_stops_info
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: finding buses to destinations, searching stops by name, getting routes at a stop, checking next bus arrivals, and listing stops on a route. The descriptions reinforce these unique functions, making misselection unlikely.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern with underscores (e.g., find_buses_to_destination, get_route_stops_info). The naming is uniform and predictable, using clear action verbs like 'find' and 'get' paired with descriptive nouns.

Tool Count5/5

With 5 tools, this server is well-scoped for a bus information system. Each tool serves a specific, necessary function in querying routes, stops, and schedules, avoiding bloat while covering core use cases effectively.

Completeness4/5

The tool set covers essential bus information queries: route discovery, stop lookup, schedule checking, and route details. A minor gap exists in lacking tools for broader operations like route planning or real-time updates, but agents can work around this with the provided tools.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches