Which integrations are available for this server?

Fetches the user's next calendar event to determine trip destination and timing. Provides route planning and directions for transit, walking, and driving. Checks real-time elevator and escalator outages on NYC transit routes to identify accessibility barriers. Queries venue accessibility information (e.g., wheelchair access) using the Overpass API.

How do I use Accessibility Mobility Context Router?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Accessibility Mobility Context Router How do I get to my next meeting?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Accessibility Mobility Context Router

by srijapentyala

Overview Schema Related Servers Score Discussions

Python

Remote

Accessibility Mobility Context Router - MCP Server

🎯 The Idea

Problem: People with disabilities face significant challenges when planning trips. Standard navigation apps don't account for:

Elevator/escalator outages in transit systems that block accessible routes
Venue accessibility information (wheelchair access, audio guides, tactile paths, etc.)
Weather conditions that affect mobility (rain, snow, extreme temperatures)
The need for extra buffer time for accessible travel
Integration with calendar events to proactively plan trips
Real-time accessibility barriers that can disrupt travel plans

Solution: An MCP (Model Context Protocol) server that fuses multiple data sources to provide people with disabilities a comprehensive, accessibility-first context package for trip planning. Instead of just "how to get there," it answers "how to get there safely and accessibly."

Key Innovation: By combining calendar intent (next meeting), real-time transit accessibility data (elevator/escalator outages), venue accessibility tags (OpenStreetMap), weather risks, and route planning, we create a context package that gives AI assistants everything they need to provide informed, accessibility-aware guidance.

Impact: This transforms trip planning from a multi-step, error-prone process into a single question: "How do I get to my next meeting?" The system automatically considers accessibility barriers, suggests alternatives, and provides evidence-linked recommendations.

🌍 Who This Helps

This MCP server benefits people across the accessibility spectrum:

Wheelchair Users: Real-time elevator/escalator outage alerts, venue wheelchair accessibility verification, accessible route planning with buffer time
Blind and Visually Impaired: Detailed route descriptions, alternative route options when primary paths are blocked, weather conditions that affect navigation
Mobility Impairments: Accessible transit options, venue accessibility information, weather-aware planning for conditions that affect mobility
People with Chronic Conditions: Buffer time recommendations, weather risk assessment, alternative routes when primary options are unavailable
Elderly Travelers: Comprehensive accessibility information, clear route alternatives, proactive barrier detection

The system's context package provides structured, evidence-backed information that AI assistants can adapt to each user's specific needs, whether they require wheelchair-accessible routes, detailed verbal descriptions, or weather-sensitive planning.

Related MCP server: Accessibility AI MCP

🚀 What This MCP Server Does

This MCP server is a specialized tool for AI assistants (like Claude) that helps people with disabilities plan accessible trips. When you ask "How do I get to my next meeting?", the server:

Fetches your next calendar event (title, time, location) from Google Calendar via ICS feed
Finds multiple route candidates (transit, walking, driving) using Google Maps Directions API
Checks for elevator/escalator outages on NYC MTA transit routes that could block accessible paths
Verifies venue accessibility (wheelchair access, accessibility features) using OpenStreetMap Overpass API
Assesses weather risks around travel time using OpenWeather API
Calculates optimal departure time with configurable buffer minutes
Fuses everything into a compact context package with citations and evidence

The result is a structured JSON package containing:

Highlights: 5 key bullets summarizing route, accessibility alerts, venue access, weather, and timing
Alternatives: Backup route options if the primary route has issues
Citations: Links to source data (maps, transit status, weather forecasts)
Metadata: Event details, origin/destination, sources used

This context package enables AI assistants to provide natural, evidence-backed answers like:

"Take the Q train from Times Square to 86th St (20 min). Leave by 3:40 PM to arrive by 4:00 PM with a 20-minute buffer. Note: There's an elevator outage at 57th St station—consider the alternative route via 96th St. The Met is wheelchair accessible. Light rain expected—bring an umbrella."

🛠️ Available Tools

The MCP server exposes two tools and one resource:

Tools

1. `ask`

Purpose: Get a concise, natural-language answer about how to reach your next meeting.

Parameters:

question (required, string): Your question, e.g., "How can I reach my next meeting?"
origin (optional, string): Starting address. If omitted, uses HOME_ADDRESS from config.
buffer_minutes (optional, integer, default: 20): Extra time buffer in minutes for accessible travel.

Returns: A text response with key highlights and recommendations, plus the full context package.

Example Request:

{
  "jsonrpc": "2.0",
  "id": "1",
  "method": "tools/call",
  "params": {
    "name": "ask",
    "arguments": {
      "question": "How can I reach my next meeting?",
      "buffer_minutes": 20
    }
  }
}

Example Response:

{
  "jsonrpc": "2.0",
  "id": "1",
  "result": {
    "content": [
      {
        "type": "text",
        "text": "- Take Q train from Times Sq-42 St to 86 St (20 min)\n- Elevator outage at 57th St station - consider alternative route\n- The Met is wheelchair accessible\n- Light rain expected around arrival time - bring an umbrella\n- Leave by 3:40 PM to arrive by 4:00 PM (20 min buffer)\n- Alternative: Take 1 train to 96th St, then walk (25 min)"
      },
      {
        "type": "text",
        "text": "{\"context\":{\"query_intent\":\"route_to_event\",\"sources_used\":[\"directions\",\"gtfs_rt_elevators\",\"osm_overpass\",\"openweather\"],\"event\":{\"title\":\"Museum Visit\",\"start_time_iso\":\"2025-11-08T16:00:00-05:00\",\"location_text\":\"The Met, 1000 5th Ave, New York, NY\"},\"origin\":{\"label\":\"Home\",\"address\":\"Times Square, New York, NY\"},\"highlights\":[{\"type\":\"route_summary\",\"text\":\"Take Q train from Times Sq-42 St to 86 St (20 min)\",\"citations\":[\"https://www.google.com/maps/dir/?saddr=Times+Square%2C+New+York%2C+NY&daddr=The+Met%2C+1000+5th+Ave%2C+New+York%2C+NY\"]},{\"type\":\"accessibility_alert\",\"text\":\"Elevator outage at 57th St station\",\"citations\":[\"https://api-endpoint.mta.info/Dataservice/mtagtfsfeeds/nyct%2Fnyct_ene.json\"]},{\"type\":\"venue_access\",\"text\":\"The Met is wheelchair accessible\",\"citations\":[\"https://overpass-api.de/api/interpreter\"]},{\"type\":\"weather_risk\",\"text\":\"Light rain expected around arrival time\",\"citations\":[\"https://api.openweathermap.org/data/2.5/forecast\"]},{\"type\":\"buffer_recommendation\",\"text\":\"Leave by 3:40 PM to arrive by 4:00 PM (20 min buffer)\",\"citations\":[]}],\"alternatives\":[{\"summary\":\"Alternative: Take 1 train to 96th St, then walk (25 min)\",\"citations\":[\"https://www.google.com/maps/dir/?saddr=Times+Square%2C+New+York%2C+NY&daddr=The+Met%2C+1000+5th+Ave%2C+New+York%2C+NY\"]}],\"raw_citations\":[\"https://www.google.com/maps/dir/?saddr=Times+Square%2C+New+York%2C+NY&daddr=The+Met%2C+1000+5th+Ave%2C+New+York%2C+NY\",\"https://api-endpoint.mta.info/Dataservice/mtagtfsfeeds/nyct%2Fnyct_ene.json\",\"https://overpass-api.de/api/interpreter\",\"https://api.openweathermap.org/data/2.5/forecast\"],\"token_estimate\":156,\"meta\":{}}}"
      }
    ]
  }
}

Note: The response contains two text items:

First item: A concise bullet-point summary answer
Second item: A JSON string containing the full context object with complete ContextPackage details, citations, and metadata

When parsed, the second item yields:

{
  "context": {
    "query_intent": "route_to_event",
    "sources_used": ["directions", "gtfs_rt_elevators", "osm_overpass", "openweather"],
    "event": {
      "title": "Museum Visit",
      "start_time_iso": "2025-11-08T16:00:00-05:00",
      "location_text": "The Met, 1000 5th Ave, New York, NY"
    },
    "origin": {
      "label": "Home",
      "address": "Times Square, New York, NY"
    },
    "highlights": [...],
    "alternatives": [...],
    "raw_citations": [...],
    "token_estimate": 156,
    "meta": {}
  }
}

2. `build_context`

Purpose: Build the full context package with all details, citations, and alternatives.

Parameters:

origin (optional, string): Starting address. If omitted, uses HOME_ADDRESS from config.
buffer_minutes (optional, integer, default: 20): Extra time buffer in minutes.

Returns: A JSON string containing the complete ContextPackage object.

Example Request:

{
  "jsonrpc": "2.0",
  "id": "2",
  "method": "tools/call",
  "params": {
    "name": "build_context",
    "arguments": {
      "buffer_minutes": 20
    }
  }
}

Example Response:

{
  "jsonrpc": "2.0",
  "id": "2",
  "result": {
    "content": [
      {
        "type": "text",
        "text": "{\"query_intent\":\"route_to_event\",\"sources_used\":[\"directions\",\"gtfs_rt_elevators\",\"osm_overpass\",\"openweather\"],\"event\":{\"title\":\"Museum Visit\",\"start_time_iso\":\"2025-11-08T16:00:00-05:00\",\"location_text\":\"The Met, 1000 5th Ave, New York, NY\"},\"origin\":{\"label\":\"Home\",\"address\":\"Times Square, New York, NY\"},\"highlights\":[{\"type\":\"route_summary\",\"text\":\"Take Q train from Times Sq-42 St to 86 St (20 min)\",\"citations\":[\"https://www.google.com/maps/dir/?saddr=Times+Square%2C+New+York%2C+NY&daddr=The+Met%2C+1000+5th+Ave%2C+New+York%2C+NY\"]},{\"type\":\"accessibility_alert\",\"text\":\"Elevator outage at 57th St station\",\"citations\":[\"https://api-endpoint.mta.info/Dataservice/mtagtfsfeeds/nyct%2Fnyct_ene.json\"]},{\"type\":\"venue_access\",\"text\":\"The Met is wheelchair accessible\",\"citations\":[\"https://overpass-api.de/api/interpreter\"]},{\"type\":\"weather_risk\",\"text\":\"Light rain expected around arrival time\",\"citations\":[\"https://api.openweathermap.org/data/2.5/forecast\"]},{\"type\":\"buffer_recommendation\",\"text\":\"Leave by 3:40 PM to arrive by 4:00 PM (20 min buffer)\",\"citations\":[]}],\"alternatives\":[{\"summary\":\"Alternative: Take 1 train to 96th St, then walk (25 min)\",\"citations\":[\"https://www.google.com/maps/dir/?saddr=Times+Square%2C+New+York%2C+NY&daddr=The+Met%2C+1000+5th+Ave%2C+New+York%2C+NY\"]}],\"raw_citations\":[\"https://www.google.com/maps/dir/?saddr=Times+Square%2C+New+York%2C+NY&daddr=The+Met%2C+1000+5th+Ave%2C+New+York%2C+NY\",\"https://api-endpoint.mta.info/Dataservice/mtagtfsfeeds/nyct%2Fnyct_ene.json\",\"https://overpass-api.de/api/interpreter\",\"https://api.openweathermap.org/data/2.5/forecast\"],\"token_estimate\":156,\"meta\":{}}"
      }
    ]
  }
}

Note: The response contains a JSON string. When parsed, it yields a ContextPackage object with the following structure:

{
  "query_intent": "route_to_event",
  "sources_used": [
    "directions",
    "gtfs_rt_elevators",
    "osm_overpass",
    "openweather"
  ],
  "event": {
    "title": "Museum Visit",
    "start_time_iso": "2025-11-08T16:00:00-05:00",
    "location_text": "The Met, 1000 5th Ave, New York, NY"
  },
  "origin": {
    "label": "Home",
    "address": "Times Square, New York, NY"
  },
  "highlights": [
    {
      "type": "route_summary",
      "text": "Take Q train from Times Sq-42 St to 86 St (20 min)",
      "citations": ["https://www.google.com/maps/dir/..."]
    },
    {
      "type": "accessibility_alert",
      "text": "Elevator outage at 57th St station",
      "citations": ["https://api-endpoint.mta.info/..."]
    },
    {
      "type": "venue_access",
      "text": "The Met is wheelchair accessible",
      "citations": ["https://overpass-api.de/..."]
    },
    {
      "type": "weather_risk",
      "text": "Light rain expected around arrival time",
      "citations": ["https://api.openweathermap.org/..."]
    },
    {
      "type": "buffer_recommendation",
      "text": "Leave by 3:40 PM to arrive by 4:00 PM (20 min buffer)",
      "citations": []
    }
  ],
  "alternatives": [
    {
      "summary": "Alternative: Take 1 train to 96th St, then walk (25 min)",
      "citations": ["https://www.google.com/maps/dir/..."]
    }
  ],
  "raw_citations": [
    "https://www.google.com/maps/dir/...",
    "https://api-endpoint.mta.info/...",
    "https://overpass-api.de/...",
    "https://api.openweathermap.org/..."
  ],
  "token_estimate": 156,
  "meta": {}
}

Resources

`context/last`

Purpose: Access the last generated context package.

URI: context/last

Returns: The most recent ContextPackage as JSON.

Example Request:

{
  "jsonrpc": "2.0",
  "id": "3",
  "method": "resources/read",
  "params": {
    "uri": "context/last"
  }
}

Example Response:

{
  "jsonrpc": "2.0",
  "id": "3",
  "result": {
    "contents": [
      {
        "type": "text",
        "text": "{\n  \"query_intent\": \"route_to_event\",\n  \"sources_used\": [\"directions\", \"gtfs_rt_elevators\", \"osm_overpass\", \"openweather\"],\n  \"event\": {\n    \"title\": \"Museum Visit\",\n    \"start_time_iso\": \"2025-11-08T16:00:00-05:00\",\n    \"location_text\": \"The Met, 1000 5th Ave, New York, NY\"\n  },\n  \"origin\": {\n    \"label\": \"Home\",\n    \"address\": \"Times Square, New York, NY\"\n  },\n  \"highlights\": [\n    {\n      \"type\": \"route_summary\",\n      \"text\": \"Take Q train from Times Sq-42 St to 86 St (20 min)\",\n      \"citations\": [\"https://www.google.com/maps/dir/?saddr=Times+Square%2C+New+York%2C+NY&daddr=The+Met%2C+1000+5th+Ave%2C+New+York%2C+NY\"]\n    },\n    {\n      \"type\": \"accessibility_alert\",\n      \"text\": \"Elevator outage at 57th St station\",\n      \"citations\": [\"https://api-endpoint.mta.info/Dataservice/mtagtfsfeeds/nyct%2Fnyct_ene.json\"]\n    },\n    {\n      \"type\": \"venue_access\",\n      \"text\": \"The Met is wheelchair accessible\",\n      \"citations\": [\"https://overpass-api.de/api/interpreter\"]\n    },\n    {\n      \"type\": \"weather_risk\",\n      \"text\": \"Light rain expected around arrival time\",\n      \"citations\": [\"https://api.openweathermap.org/data/2.5/forecast\"]\n    },\n    {\n      \"type\": \"buffer_recommendation\",\n      \"text\": \"Leave by 3:40 PM to arrive by 4:00 PM (20 min buffer)\",\n      \"citations\": []\n    }\n  ],\n  \"alternatives\": [\n    {\n      \"summary\": \"Alternative: Take 1 train to 96th St, then walk (25 min)\",\n      \"citations\": [\"https://www.google.com/maps/dir/?saddr=Times+Square%2C+New+York%2C+NY&daddr=The+Met%2C+1000+5th+Ave%2C+New+York%2C+NY\"]\n    }\n  ],\n  \"raw_citations\": [\n    \"https://www.google.com/maps/dir/?saddr=Times+Square%2C+New+York%2C+NY&daddr=The+Met%2C+1000+5th+Ave%2C+New+York%2C+NY\",\n    \"https://api-endpoint.mta.info/Dataservice/mtagtfsfeeds/nyct%2Fnyct_ene.json\",\n    \"https://overpass-api.de/api/interpreter\",\n    \"https://api.openweathermap.org/data/2.5/forecast\"\n  ],\n  \"token_estimate\": 156,\n  \"meta\": {}\n}"
      }
    ]
  }
}

Note: The response contains a formatted JSON string of the last generated ContextPackage. If no context has been built yet, it returns an empty object {}.

📦 Setup Instructions

Prerequisites

Python 3.9 or higher
Virtual environment tool (recommended: uv or venv)
(Optional) API keys for enhanced functionality (see below)

Step 1: Clone and Navigate

cd D:\Datathon

Step 2: Create Virtual Environment

Using uv (recommended):

# Install uv if not already installed
# Windows PowerShell:
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

# Create virtual environment
uv venv

# Activate (Windows PowerShell)
.\.venv\Scripts\activate

Using venv:

python -m venv .venv

# Activate (Windows PowerShell)
.\.venv\Scripts\activate

Step 3: Install Dependencies

# Using uv
uv pip install -r requirements.txt

# Or using pip
pip install -r requirements.txt

Step 4: Configure Environment Variables

Create a .env file in the project root:

# Required: Set your home address (origin for trips)
HOME_ADDRESS=Times Square, New York, NY

# Optional: Default city code
DEFAULT_CITY=nyc

# Optional: Google Calendar ICS URL (private read-only feed)
# Get this from: Google Calendar → Settings → Your Calendar → Integrate Calendar → "Secret address in iCal format"
GOOGLE_CALENDAR_ICS_URL=https://calendar.google.com/calendar/ical/your_secret_hash/basic.ics

# Optional: Google Maps API Key (for live directions)
GOOGLE_MAPS_API_KEY=your_google_maps_api_key_here

# Optional: OpenWeather API Key (for weather forecasts)
OPENWEATHER_API_KEY=your_openweather_api_key_here

# Optional: MTA API Key (not required - MTA JSON feeds are public)
MTA_API_KEY=

# Optional: Mock mode (auto-enabled if API keys missing)
MOCK_MODE=false

# Optional: Request timeout in seconds
REQUEST_TIMEOUT_SECONDS=3.0

# Optional: Weather units (metric or imperial)
WEATHER_UNITS=metric

Note: The server works in mock mode if API keys are missing, providing deterministic demo data. This is perfect for testing and demos.

Step 5: Run the MCP Server

For stdio mode (used by Claude Desktop):

python -m app.mcp_server

The server will wait for JSON-RPC messages on stdin and respond on stdout.

For REST API mode (optional):

uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload

🔌 Connecting to Claude Desktop

To use this MCP server with Claude Desktop:

Locate Claude Desktop config file:
- Windows: %APPDATA%\Claude\claude_desktop_config.json
- Or: C:\Users\<YourUsername>\AppData\Roaming\Claude\claude_desktop_config.json
Edit or create the config file:

{
  "mcpServers": {
    "mobility": {
      "command": "D:\\Datathon\\.venv\\Scripts\\python.exe",
      "args": ["-m", "app.mcp_server"],
      "workingDirectory": "D:\\Datathon",
      "env": {
        "PYTHONPATH": "D:\\Datathon",
        "PYTHONUNBUFFERED": "1",
        "HOME_ADDRESS": "Times Square, New York, NY",
        "DEFAULT_CITY": "nyc",
        "MOCK_MODE": "false"
      }
    }
  }
}

Important:

Use forward slashes or escaped backslashes (\\) in paths
Set PYTHONPATH to your project root
Set PYTHONUNBUFFERED=1 for proper stdio communication
Add any environment variables you need in the env section

Restart Claude Desktop completely
Test in Claude: Ask "How do I get to my next meeting?" or "Use the ask tool to help me plan my route"

🏗️ Architecture

app/
├── mcp_server.py          # MCP server entry point (stdio JSON-RPC)
├── main.py                # FastAPI REST API (optional)
├── config.py              # Settings and runtime state
├── models/
│   └── schemas.py         # Pydantic models (ContextPackage, etc.)
└── services/
    ├── calendar.py        # Google Calendar ICS integration
    ├── directions.py      # Google Maps Directions API
    ├── geocode.py         # Address geocoding (Google/Nominatim)
    ├── transit.py         # NYC MTA elevator/escalator outages
    ├── osm.py             # OpenStreetMap venue accessibility
    ├── weather.py         # OpenWeather API integration
    ├── fusion.py          # Route scoring and context fusion
    ├── formatter.py       # Context package building
    └── llm.py             # Gemini integration (optional)
└── utils/
    └── http.py           # Shared HTTP client with timeouts

Data Flow

Input: User asks "How do I get to my next meeting?" via MCP tool
Calendar: Fetch next event (title, time, location) from ICS feed
Geocoding: Resolve location text to lat/lng coordinates
Parallel Data Fetching:
- Directions API → Route candidates
- MTA API → Elevator/escalator outages
- OSM Overpass → Venue wheelchair tag
- OpenWeather → Weather forecast
Fusion: Score routes, identify best option, generate context bullets
Output: Structured context package with highlights, alternatives, citations

Key Design Decisions

Mock Mode: Graceful degradation when API keys are missing (deterministic demo data)
Timeout Protection: All HTTP requests have configurable timeouts (default 3s)
Citation Links: Every piece of information includes source links for verification
Buffer Time: Configurable extra time for accessible travel (default 20 minutes)
Error Handling: Server continues processing even if individual data sources fail

📊 Context Package Structure

The ContextPackage returned by tools includes:

{
  "query_intent": "route_to_event",
  "sources_used": [
    "directions",
    "gtfs_rt_elevators",
    "osm_overpass",
    "openweather"
  ],
  "event": {
    "title": "Museum Visit",
    "start_time_iso": "2025-11-08T16:00:00-05:00",
    "location_text": "The Met, 1000 5th Ave, New York, NY"
  },
  "origin": {
    "label": "Home",
    "address": "Times Square, New York, NY"
  },
  "highlights": [
    {
      "type": "route_summary",
      "text": "Take Q train from Times Sq-42 St to 86 St (20 min)",
      "citations": ["https://www.google.com/maps/dir/..."]
    },
    {
      "type": "accessibility_alert",
      "text": "Elevator outage at 57th St station",
      "citations": ["https://api-endpoint.mta.info/..."]
    },
    {
      "type": "venue_access",
      "text": "The Met is wheelchair accessible",
      "citations": ["https://overpass-api.de/..."]
    },
    {
      "type": "weather_risk",
      "text": "Light rain expected around arrival time",
      "citations": ["https://api.openweathermap.org/..."]
    },
    {
      "type": "buffer_recommendation",
      "text": "Leave by 3:40 PM to arrive by 4:00 PM (20 min buffer)",
      "citations": []
    }
  ],
  "alternatives": [
    {
      "summary": "Alternative: Take 1 train to 96th St, then walk (25 min)",
      "citations": ["https://www.google.com/maps/dir/..."]
    }
  ],
  "raw_citations": [
    "https://www.google.com/maps/dir/...",
    "https://api-endpoint.mta.info/..."
  ]
}

🔑 API Keys (Optional)

The server works without API keys (mock mode), but for production use:

Google Calendar ICS URL

How to get: Google Calendar → Settings → Your Calendar → Integrate Calendar → Copy "Secret address in iCal format"
Why: Fetches your next event automatically

Google Maps API Key

How to get: Google Cloud Console → Enable "Directions API" → Create API key
Why: Provides live route planning with transit, walking, and driving options

OpenWeather API Key

How to get: OpenWeatherMap → Sign up → Get API key
Why: Weather forecasts around travel time

MTA API Key

Not required: MTA JSON feeds are public (no key needed)
Why: Real-time elevator/escalator outage data for NYC transit

🧪 Testing

Manual Testing (stdio mode)

The MCP server communicates via JSON-RPC over stdio. You can test it manually:

python -m app.mcp_server

Then send JSON-RPC messages (the server will respond).

REST API Testing (optional)

If you run the FastAPI server:

uvicorn app.main:app --host 0.0.0.0 --port 8000

Test endpoints:

GET /health - Health check
POST /config/home - Set home address
POST /build_context - Build context package
GET /context/last - Get last context package

🎯 Use Cases

Proactive Trip Planning: "How do I get to my next meeting?" → Automatic route planning with accessibility checks
Accessibility Alerts: Real-time notifications about elevator outages that affect your route
Venue Verification: Check if a destination is wheelchair accessible before you go
Weather-Aware Planning: Know if weather will affect your travel
Alternative Routes: Get backup options if your primary route has issues

📝 License

MIT

🤝 Contributing

This is a production-ready MCP server for accessibility-aware trip planning. The codebase is structured for easy extension:

Add new transit systems (currently NYC MTA)
Integrate additional data sources
Enhance route scoring algorithms
Add support for other calendar providers

🐛 Troubleshooting

Server won't start

Check Python version: python --version (needs 3.9+)
Verify dependencies: pip list
Check PYTHONPATH is set correctly

Tools not working in Claude

Verify MCP server config JSON syntax
Check Claude Desktop logs: %APPDATA%\Claude\Logs\
Ensure PYTHONUNBUFFERED=1 is set in config
Restart Claude Desktop after config changes

No calendar events found

Verify GOOGLE_CALENDAR_ICS_URL is correct
Check that your calendar has upcoming events with locations
Server falls back to mock event if ICS fails

Mock mode always enabled

Set MOCK_MODE=false in .env or config
Provide at least one API key (Google Maps recommended)

📚 Additional Resources

🔮 Future Improvements

This MVP provides a solid foundation for accessibility-aware trip planning. Potential future enhancements include:

Expanded Transit Coverage: Support for additional transit systems beyond NYC MTA (e.g., other major cities' transit APIs)
Enhanced Accessibility Data: Integration with crowdsourced accessibility platforms and venue-specific accessibility databases
Personalization: User preference profiles for accessibility needs, preferred transit modes, and buffer time preferences
Advanced Route Intelligence: Machine learning-based route scoring and predictive outage detection using historical patterns
Multi-Calendar Support: Integration with additional calendar providers (Outlook, Apple Calendar, etc.)

These improvements would enhance the MCP server's capabilities while building on the current accessibility-first foundation.

This server cannot be installed

license - permissive license

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

–Release cycle

–Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly
Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
OpenAI
open source

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/srijapentyala/Mobility-MCP-Server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

Accessibility Mobility Context Router - MCP Server

🎯 The Idea

🌍 Who This Helps

🚀 What This MCP Server Does

🛠️ Available Tools

Tools

1. ask

2. build_context

Resources

context/last

📦 Setup Instructions

Prerequisites

Step 1: Clone and Navigate

Step 2: Create Virtual Environment

Step 3: Install Dependencies

Step 4: Configure Environment Variables

Step 5: Run the MCP Server

🔌 Connecting to Claude Desktop

🏗️ Architecture

Data Flow

Key Design Decisions

📊 Context Package Structure

🔑 API Keys (Optional)

Google Calendar ICS URL

Google Maps API Key

OpenWeather API Key

MTA API Key

🧪 Testing

Manual Testing (stdio mode)

REST API Testing (optional)

🎯 Use Cases

📝 License

🤝 Contributing

🐛 Troubleshooting

Server won't start

Tools not working in Claude

No calendar events found

Mock mode always enabled

📚 Additional Resources

🔮 Future Improvements

Maintenance

Resources

Looking for Admin?

Latest Blog Posts

MCP directory API

1. `ask`

2. `build_context`

`context/last`