mcp · Global

ghg-calculator

Open source GHG Protocol emissions calculator — 967 factors, all 3 scopes, CLI, MCP server, Claude Code skill

Claim this listing

Represent ghg-calculator? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.

Data offered docs-verified: 967 emission factors across EPA Hub, eGRID, DEFRA, USEEIO, Ember and EXIOBASE · Scope 1, 2 and 3 emissions calculation · Scope 2 location-based and market-based results · GWP values (AR5 and AR6) · Unit conversion · Interactive HTML report generation
Coverage llm-inferred: US (EPA, eGRID, USEEIO); UK and international transport, materials and waste (DEFRA); electricity for 120 countries (Ember); EU, CN, JP, IN, BR and RU multi-regional (EXIOBASE)
Resolution llm-inferred: US eGRID subregion level (27 subregions); country level for international electricity (120 countries)
Formats llm-inferred: JSON · HTML · MCP stdio
Access docs-verified: Free and open source under MIT licence; no API key, paid API or proprietary database required; local install needs Python 3.11+ and uv

Use cases llm-inferred: UK Scope 2 electricity for a site, depot or pumping station using the Ember GB factor (country 'GB') · Scope 1 combustion emissions from site natural gas or diesel records for a civils or environmental project · Spend-based Scope 3 screening of purchased services using USEEIO, and materials using DEFRA factors · Electricity scenario comparison across grid mixes for a drainage or water-infrastructure options appraisal
Audience llm-inferred: environmental consultants · ESG and sustainability analysts · civils engineers assessing construction or materials emissions · climate tech developers building AI agent tools

Constraints llm-inferred: Repository URL differs between ENTRY (gaiaaiagent/ghg-calculator) and DOCS clone command (starrybodies/ghg-calculator); confirm the canonical source before installing · ENTRY tools list mixes the 8 MCP tools with library dependencies (pydantic, pint, pandas, plotly, fastmcp, jinja2) · Region 'Global' overstates coverage: factor sources are US-centric (EPA, eGRID, USEEIO), with UK coverage limited to DEFRA and Ember GB electricity · Spend-based Scope 3 results are screening-grade; accuracy depends on input data quality · Local install only (Python 3.11+ and uv); no hosted endpoint is described · No update frequency or factor vintage dates are stated, so factor currency is unverified · MCP input schemas are not given in DOCS

Licence: Unknown — check provider terms
Authentication: No API key required (repository README, auto-extracted; check upstream requirements)
GitHub stars: 3
Last commit: 17/02/2026
Last successful page check: 14/10/2026
Page health: healthy
Package: Not recorded
Verification: Not independently verified

Auto-extracted, unverified fields: tools, install, auth. Check upstream documentation.

Tools/install/auth auto-extracted from README; quality score heuristic (stars, recency, tool count, licence).

Metadata observed 15/10/2026 · research sweep: github-search