빌니우스 대중교통 데이터 접근 기능을 대규모 언어 모델(LLM)에 제공하는 모델 컨텍스트 프로토콜(MCP) 서버 구현입니다. 이 프로젝트는 MCP 표준을 사용하여 실시간 교통 데이터로 LLM 기능을 확장하는 방법을 보여줍니다.
모델 컨텍스트 프로토콜(MCP)은 대규모 언어 모델(LLM)이 외부 도구 및 데이터에 안전하게 액세스할 수 있도록 하는 표준입니다. MCP를 통해 LLM은 다음과 같은 작업을 수행할 수 있습니다.
실시간 또는 로컬 데이터에 액세스
외부 함수 claude_desktop_config.json을 호출합니다.
시스템 리소스와 상호 작용
일관된 도구 인터페이스 유지
이 프로젝트는 LLM에 빌니우스 대중교통 데이터 도구를 제공하는 MCP 서버를 구현하여 LLM이 대중교통 정류장과 노선에 대한 질의에 답할 수 있도록 합니다.
서버는 다음과 같은 MCP 도구를 제공합니다.
find_stops : 이름으로 대중교통 정류장 검색
지엑스피1
find_closest_stop : 주어진 좌표에서 가장 가까운 대중교통 정류장을 찾습니다.
{
coordinates: string; // Format: "latitude, longitude" (e.g., "54.687157, 25.279652")
}Claude 개발 환경에 MCP 서버를 추가하려면 claude_desktop_config.json 파일에 다음 구성을 추가하세요.
{
"mcpServers": {
"vilnius_transport": {
"command": "uv",
"args": [
"--directory",
"path/vilnius-transport-mcp-server/src/vilnius_transport_mcp",
"run",
"transport.py"
]
}
}
}참고: 로컬 설치에 맞게 디렉토리 경로를 조정하세요.
클라이언트를 실행하려면:
uv run client.py path/src/vilnius_transport_mcp/transport.pyFind the closest public transport stop to given coordinates
| Name | Required | Description | Default |
|---|---|---|---|
| coordinates | Yes | Coordinates as 'latitude, longitude' (e.g., '54.687157, 25.279652') |
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 mentions 'find' but doesn't clarify if this is a read-only operation, how results are returned (e.g., distance, stop details), potential errors (e.g., invalid coordinates), or performance aspects like rate limits. The description lacks critical behavioral traits needed for safe and effective invocation.
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, clear sentence that directly states the tool's function without unnecessary words or fluff. It is front-loaded with the core action and resource, making it efficient and easy to parse, which is ideal for conciseness in tool descriptions.
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 lack of annotations and output schema, the description is incomplete for a tool that likely returns complex data (e.g., stop names, distances). It doesn't explain what the output includes, how 'closest' is determined (e.g., walking distance, straight-line), or error handling. For a tool with one parameter but potentially rich behavior, more context is needed to guide an agent effectively.
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, with the 'coordinates' parameter well-documented in the schema (e.g., format 'latitude, longitude'). The description adds no additional parameter semantics beyond what the schema provides, such as coordinate range limits or examples of valid inputs. Given the high schema coverage, a baseline score of 3 is appropriate as the schema handles the heavy lifting.
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 'find' and the resource 'closest public transport stop' with the condition 'to given coordinates', making the purpose specific and actionable. However, it doesn't explicitly differentiate from the sibling tool 'find_stops', which might handle multiple stops or different criteria, leaving some ambiguity in sibling differentiation.
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 like 'find_stops', nor does it mention any prerequisites, exclusions, or contextual factors (e.g., transport modes, time of day). It only states the basic function without usage context, which limits its helpfulness for an agent selecting between tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for public transport stops by name
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Full or partial name of the stop to search for |
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. The description states it's a search operation, implying it's likely read-only and non-destructive, but it doesn't confirm this or provide details on permissions, rate limits, response format, or error handling. For a tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence: 'Search for public transport stops by name'. It's front-loaded with the core purpose, has zero wasted words, and is appropriately sized for a simple search tool. Every part of the sentence earns its place by specifying the action, target, and method.
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 low complexity (1 parameter, no output schema, no annotations), the description is minimally complete. It states what the tool does but lacks details on behavioral traits, usage context, and output expectations. With no output schema, the description doesn't explain return values, which is a gap. However, for a simple search tool, it provides enough to understand the basic function.
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 schema description coverage is 100%, with the parameter 'name' fully documented in the schema as 'Full or partial name of the stop to search for'. The description adds no additional parameter information beyond what the schema provides, such as examples or edge cases. According to the rules, with high schema coverage (>80%), the baseline score is 3 when no param info is added in the description.
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's purpose: 'Search for public transport stops by name' specifies the verb (search), resource (public transport stops), and mechanism (by name). It's not tautological and distinguishes itself from the sibling tool 'find_closest_stop' by focusing on name-based search rather than proximity. However, it doesn't explicitly differentiate from potential other search methods beyond the sibling.
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. It doesn't mention the sibling tool 'find_closest_stop' or any other potential tools, nor does it specify contexts where name-based search is preferred over proximity-based search. Usage is implied by the description but not explicitly stated.
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.
v1.0.0find_closest_stopfind_stopsScored across 2 tools
The two tools have clearly distinct purposes: find_closest_stop locates the nearest stop based on coordinates, while find_stops searches by name. There is no overlap in functionality, making it easy for an agent to choose the right tool for each scenario.
Both tools follow a consistent verb_noun naming pattern (find_closest_stop, find_stops) with the same verb 'find'. The naming is predictable and readable, showing no deviations in style or convention.
With only two tools, the server feels thin for a public transport domain. While the tools cover basic stop lookup, there are likely missing operations such as route planning, schedule retrieval, or real-time arrivals, which are common in transport systems. The count is too low for the apparent scope.
The tool surface is significantly incomplete for a transport server. It lacks core functionalities like getting routes, schedules, or vehicle positions, which are essential for comprehensive transport queries. Agents will face dead ends when trying to perform common tasks beyond stop lookup.
The Ferryhopper MCP server is a connector for LLMs and AI Agents in maritime travel that exposes ferry routes, schedules, and booking options. It enables AI assistants to search ports and connections across 33 countries and 190+ ferry operators, provide real-time ferry itineraries with indicative prices, and assist users with planning island-hopping or multi-leg journeys by processing natural language queries about ferry times, passenger counts, and travel durations.
A Model Context Protocol server for Wix AI tools
The official Model Context Protocol server for Ambee. It gives any MCP-compatible AI assistant — Claude, ChatGPT, Cursor, VS Code, Ollama, and more direct access to live air quality, pollen, and weather data. To get started, including information on signing up and obtaining your Ambee key, check out the Ambee documentation on https://docs.ambeedata.com
Public Data Ukraine Mcp connects AI agents to real public APIs via MCP. Tools include
