Skip to main content

climate-risk-mcp-server

MCP server for climate risk assessment and emissions data. Gives AI agents access to CO2 emissions by country and sector, climate projections, and risk assessments for heat, flooding, and drought.

Built for ESG analysis, CSRD compliance reporting, and climate due diligence.

Why Climate Risk Data?

  • EU CSRD (Corporate Sustainability Reporting Directive) requires 50,000+ companies to report climate risks starting 2025
  • TCFD/ISSB frameworks demand quantitative climate scenario analysis
  • ESG investors need emissions data and physical risk assessments for portfolio decisions
  • Supply chain due diligence requires climate risk screening of locations worldwide

Tools (6)

Tool Description
get_emissions CO2 emissions by country via Climate TRACE (195+ countries)
get_sector_emissions_tool Emissions by sector (power, transport, agriculture, etc.)
get_climate_projection Temperature & precipitation projections (RCP/SSP scenarios)
compare_countries Compare emissions between multiple countries
get_emission_trends Historical emission trends over 10-30 years
assess_climate_risk Risk assessment for any location (heat, flooding, drought)

Data Sources

  • Climate TRACE — Independent greenhouse gas emissions tracking for every country and major sector. Free, no API key needed.
  • Open-Meteo Climate API — Climate projections based on CMIP5/CMIP6 models. Free, no API key needed.
  • NOAA CDO — Historical climate observations. Free token with generous limits.

Installation

pip install climate-risk-mcp-server

Configuration

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "climate-risk": {
      "command": "climate-risk-server"
    }
  }
}

With uvx (no install needed)

{
  "mcpServers": {
    "climate-risk": {
      "command": "uvx",
      "args": ["climate-risk-mcp-server"]
    }
  }
}

Optional: NOAA Token

For historical climate observations, set a NOAA token (free):

export NOAA_TOKEN="your-token-here"

Register at: https://www.ncdc.noaa.gov/cdo-web/token

Usage Examples

Get Germany's CO2 emissions:

"What are Germany's CO2 emissions?"

Compare countries:

"Compare emissions between USA, China, and India"

Climate risk for a location:

"Assess climate risk for Munich (48.14, 11.58)"

Sector analysis:

"Show power sector emissions for the UK"

Future projections:

"What are the temperature projections for Berlin under RCP 8.5?"

Climate Scenarios

Scenario Description Warming by 2100
RCP 2.6 / SSP1-2.6 Strong mitigation ~1.5°C
RCP 4.5 / SSP2-4.5 Moderate mitigation ~2.5°C
RCP 8.5 / SSP5-8.5 Business as usual ~4.5°C

License

MIT

Metadata

Release files for climate-risk-mcp-server 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for climate-risk-mcp-server 0.1.0
File Size Uploaded
climate_risk_mcp_server-0.1.0.tar.gz 10.1 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for climate-risk-mcp-server 0.1.0
File Interpreter ABI Platform
climate_risk_mcp_server-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 22.8 kB

Release files / climate_risk_mcp_server-0.1.0.tar.gz

Download URL climate_risk_mcp_server-0.1.0.tar.gz
Size 10.1 kB
Tags Source
SHA-256 checksum
How to use checksums
3a0f137a701f9e056e09b2d4a4161ad1f04dac2b738736673e5704865c956988
BLAKE2b-256 checksum
How to use checksums
51496f4956b24ecaaa814c47ab037d3be6215c1e2ab1d7f8507d69a147127354
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.3

Release files / climate_risk_mcp_server-0.1.0-py3-none-any.whl

Download URL climate_risk_mcp_server-0.1.0-py3-none-any.whl
Size 12.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
d418e9a890715ee72d06d1ebebef9178e78f26774f2b1683bf6321b35d126f72
BLAKE2b-256 checksum
How to use checksums
52f85b6b607c79cfb8230205141bac0150d4d8015fa1b56921b606c84d98e9fb
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.3

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page