Skip to main content
Glama
harshil1712

Berlin Transport MCP Server

by harshil1712

MCP-Server des Berliner Verkehrs

Ein MCP-Server, der über die API des VBB (Verkehrsverbund Berlin-Brandenburg) Zugriff auf die Daten des Berliner öffentlichen Nahverkehrs bietet. Dieser Server umschließt die API v6.vbb.transport.rest .

Verfügbare Tools

1. Suchstopps

Suche nach Haltestellen des öffentlichen Nahverkehrs in Berlin-Brandenburg.

Parameter:

  • query (string): Suchanfrage für Haltestellen

2. get_departures

Erhalten Sie bevorstehende Abfahrten für eine bestimmte Haltestelle.

Parameter:

  • stop_id (Zeichenfolge): Haltestellen-ID, für die Abfahrten abgerufen werden sollen

  • results (Zahl, optional): Anzahl der zurückzugebenden Ergebnisse

3. get_journeys

Erhalten Sie Reiseoptionen von einer Haltestelle zur anderen.

Parameter:

  • from (Zeichenfolge): ID der Ursprungshaltestelle

  • to (Zeichenfolge): Zielhaltestellen-ID

  • departure (Zeichenfolge, optional): Abfahrtszeit (z. B. „morgen 14 Uhr“)

  • results (Zahl, optional): Anzahl der zurückzugebenden Ergebnisse

Related MCP server: BVG MCP Server

Verbinden Sie Claude Desktop mit Ihrem MCP-Server

Sie können auch von lokalen MCP-Clients aus eine Verbindung zu Ihrem Remote-MCP-Server herstellen, indem Sie den MCP-Remote-Proxy verwenden.

Um von Claude Desktop aus eine Verbindung zu Ihrem MCP-Server herzustellen, folgen Sie der Schnellstartanleitung von Anthropic und gehen Sie in Claude Desktop zu Einstellungen > Entwickler > Konfiguration bearbeiten.

Update mit dieser Konfiguration:

{
  "mcpServers": {
    "calculator": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://berlin-transport.mcp-tools.app/sse"  // or if local http://localhost:8787/sse
      ]
    }
  }
}

Starten Sie Claude neu und die Tools sollten verfügbar werden.

API-Dokumentation

Weitere Einzelheiten zur zugrunde liegenden API finden Sie unter v6.vbb.transport.rest/getting-started.html .

Erste Schritte:

Für Worker bereitstellen

Dadurch wird Ihr MCP-Server unter einer URL wie der folgenden bereitgestellt: remote-mcp-server-authless.<your-account>.workers.dev/sse

Alternativ können Sie die folgende Befehlszeile verwenden, um den Remote-MCP-Server auf Ihrem lokalen Computer zu erstellen:

npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless

Anpassen Ihres MCP-Servers

Um dem MCP-Server Ihre eigenen Tools hinzuzufügen, definieren Sie jedes Tool innerhalb der init() Methode von src/index.ts mit this.server.tool(...) .

Mit Cloudflare AI Playground verbinden

Sie können vom Cloudflare AI Playground, einem Remote-MCP-Client, eine Verbindung zu Ihrem MCP-Server herstellen:

  1. Gehen Sie zu https://playground.ai.cloudflare.com/

  2. Geben Sie die URL Ihres bereitgestellten MCP-Servers ein ( remote-mcp-server-authless.<your-account>.workers.dev/sse ).

  3. Sie können Ihre MCP-Tools jetzt direkt vom Spielplatz aus verwenden!

Available Tools

3 tools
get_departuresD
ParametersJSON Schema
NameRequiredDescriptionDefault
stop_idYesStop ID to get departures for
resultsNoNumber of results to return

TDQS

D1/5.0
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

get_journeysD
ParametersJSON Schema
NameRequiredDescriptionDefault
fromYesOrigin stop ID
toYesDestination stop ID
departureNoDeparture time (e.g. tomorrow 2pm)
resultsNoNumber of results to return

TDQS

D1/5.0
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

search_stopsD
ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query for stops

TDQS

D1/5.0
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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. 3 tool updates
    • First observedget_departures
    • First observedget_journeys
    • First observedsearch_stops

TDQS

D1.8/5.0

Scored across 3 tools

Disambiguation4/5

The three tools have distinct purposes: get_departures likely retrieves departure times, get_journeys handles route planning, and search_stops finds stops or stations. While there is some potential overlap between get_departures and get_journeys (both involve travel information), the names suggest clear enough separation for an agent to differentiate them effectively.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with snake_case: get_departures, get_journeys, and search_stops. This uniformity makes the tool set predictable and easy to understand, with no deviations in naming style.

Tool Count3/5

With only 3 tools, the server feels thin for a transport domain that typically requires more operations like route details, fare information, or service alerts. While it covers basic functions, the count is borderline low for comprehensive transport-related tasks.

Completeness2/5

The tool set has significant gaps for a transport server. It lacks essential operations such as getting route details, checking fares, accessing service status or alerts, and managing user preferences. This incomplete coverage will likely cause agent failures when handling common transport queries beyond basic departure and journey lookups.

Maintenance

ActivityStale
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers