Skip to main content
Glama
Sign In
mcp-disaster-server

mcp-disaster-server

by yanaSelin
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

mcp-disaster-server

MCP server for querying the Kaggle "All Natural Disasters 1900-2021 / EOSDIS" CSV dataset via pandas.

Exposes two tools over the stdio MCP protocol:

  • search_disasters — filter records by disaster type, country, and year range

  • get_disaster_statistics — aggregate statistics by dimension (country, continent, year, etc.)

Usage with uvx

DISASTER_CSV_PATH=/path/to/natural_disasters.csv uvx --from . mcp-disaster-server

Or if published to PyPI:

DISASTER_CSV_PATH=/path/to/natural_disasters.csv uvx mcp-disaster-server

Related MCP server: wems-mcp-server

Install as editable package (for development)

pip install -e .

After installation the entry point is available as:

DISASTER_CSV_PATH=/path/to/natural_disasters.csv mcp-disaster-server

Environment

Variable

Required

Description

KAGGLE_API_TOKEN

First run only

Kaggle API token for auto-downloading the CSV on first launch. Not needed if the CSV already exists at DISASTER_CSV_PATH.

DISASTER_CSV_PATH

No

Override the CSV path. Defaults to ~/.mcp-disaster-server/natural_disasters.csv. Useful in tests or CI to point at the 30-row sample fixture.

Data

The server auto-downloads the Kaggle All Natural Disasters 1900-2021 / EOSDIS dataset on first launch (requires KAGGLE_API_TOKEN) and caches it at ~/.mcp-disaster-server/natural_disasters.csv. Subsequent runs reuse the cached file. Column names are normalized at startup (lowercase, underscores, no punctuation).

See docs/architecture.md for design decisions.

This server cannot be deployed

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

Maintenance

ActivityStale
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • HF Dataset MCP

    cfahlgren1
    A
    license
    A
    quality
    D
    maintenance
    An MCP server for the Hugging Face Dataset Viewer API that enables searching, fetching, and filtering datasets on the Hugging Face Hub. It allows users to explore schemas, perform full-text searches, and analyze dataset statistics through natural language.
    10
    MIT

  • wems-mcp-server

    heliosarchitect
    A
    license
    Not graded
    quality
    D
    maintenance
    A powerful MCP server that connects AI assistants to authoritative natural hazard data sources, enabling monitoring of earthquakes, tsunamis, volcanoes, and solar events with configurable alerts and webhooks.
    21 PyPI
    1
    MIT

  • quake-mcp

    adamcwade
    A
    license
    A
    quality
    C
    maintenance
    MCP server wrapping the USGS Earthquake Hazards API, enabling AI assistants to search the global earthquake catalog, look up event details, count quakes, find 'Did You Feel It' reports, and read realtime feeds.
    5
    MIT

  • mcp-hazards

    jsuich
    A
    license
    Not graded
    quality
    C
    maintenance
    An MCP server that gives AI agents grounded access to US natural-hazard data — weather alerts, forecasts, earthquakes, and FEMA flood zones — from free, keyless US government APIs.
    MIT