Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@eea-climate-data-mcp show greenhouse gas emissions for Germany from 1990"
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.
Schema-aware, read-only access to European climate data published through the public Discodata service of the European Environment Agency (EEA).
This MVP is a conditional go. It supports the verified GHG Inventory and Policies and Measures databases. A current projections database was not visible in Discodata metadata during the 2026-07-19 spike, so WEM/WAM comparison is not claimed.
This is an independent, unofficial client. The EEA and reporting countries remain the authoritative sources.
This repository is an experimental proof of concept, not a production service.
Interfaces, upstream schemas, and the undocumented execution allowlist may change.
SeeTODO.md.
Install the CLI and MCP server as isolated commands:
uv tool install eea-climate-data-mcp
eu-climate --helpDevelopment checkout:
uv sync --extra test
uv run eu-climate databases list
uv run eea-climate-data-mcpThe MCP command uses stdio transport. No credentials are required.
Claude Code:
claude mcp add --scope user eu-climate -- uvx eea-climate-data-mcpCodex CLI:
codex mcp add eu-climate -- uvx eea-climate-data-mcpOne-click editor installation:
Client | Install |
VS Code | |
Cursor |
|
Related MCP server: mcp-data-europa
uv run eu-climate series emissions --country DE --sector total \
--accounting-scope without_lulucf --start-year 1990
uv run eu-climate sectors search transport
uv run eu-climate series emissions --country HU --sector 1.A.3 --start-year 1990
uv run eu-climate measures list --country Hungary --status Implemented --sector Transport
uv run eu-climate measures get --country Hungary --measure-id 4
uv run eu-climate tables describe \
--database GHG_Inventory --version latest --table ghg_value
uv run eu-climate values distinct \
--database GHGPAMS --version latest \
--table annexIX_flat_view_PaMs_elasticsearch --column Country
uv run eu-climate sql validate --query-file examples/country_inventory_counts.sql
uv run eu-climate sql run --query-file examples/country_inventory_counts.sql \
--max-rows 100 --page-size 100All execution paths use the same service and SQL guardrails. Queries must be one
parsed SELECT, fully qualify every table as [database].[version].[table], use
allowlisted databases and versions, and remain within the requested bound. DDL, DML,
CTEs, SELECT INTO, system schemas, and unaliased computed columns are rejected.
Domain | Database | Country field | Live coverage | Status |
National GHG inventory |
|
| 31 countries plus |
|
Policies and Measures |
|
| 30 countries |
|
GHG projections | Not found in live metadata | — | — | Outside MVP |
Country identifiers differ between datasets: inventory uses codes such as DE, FR,
and HU, while Policies and Measures uses labels such as Germany, France, and
Hungary. Use metadata discovery or values distinct before constructing cross-domain
queries. EUA is an aggregate, not a country.
latest is mutable. Use a concrete version or revision for reproducible analysis when
the upstream exposes one. The latest inventory year is a published reporting year, not
a real-time emissions figure.
The get_emissions_series MCP tool and series emissions CLI command resolve the
appropriate inventory variable and sort results client-side because upstream rejects
ORDER BY on some ghg_value queries. sector accepts total or an IPCC sector
code at any depth (1, 1.A, 1.A.3); discover codes with
search_emission_sectors/describe_emission_sector (sectors search|describe).
Parent sectors already include their children — never sum a sector with its parent
or children.
The list_measures/get_measure tools (measures list|get CLI) expose the Policies
and Measures database as a searchable descriptive catalogue. Structured ex-ante and
ex-post effect values are sparse (several countries, including Hungary, report none),
so get_measure returns explicit quantification semantics — reported vs
not_reported — and missing values must not be read as zero impact. The catalogue is
deliberately not a ranking or impact-estimation source. Every result includes a query hash, retrieval
time, table references, reporting status, source links, and warnings.
Machine-readable output goes to stdout and diagnostics to stderr. Exit codes:
Code | Meaning |
| Success |
| Invalid or unsafe query/argument |
| Upstream unavailable or invalid response |
| Metadata object not found |
docs/RECIPES.md contains six reproducible investigation recipes (trend, sectoral change, road-transport contribution, PaMs reporting completeness, sector quantification gaps, trend × measure stock) with exact commands, formulas, query hashes, and caveats.
See docs/SPIKE-REVIEW.md for evidence, limitations, and next scope. The original Hungary-focused brief is retained as historical context in docs/SPIKE-hun-climate-policy-mcp.md.
uv run pytest
uv run ruff format --check src tests
uv run ruff check src tests
uv run mypy src tests
uv run python scripts/live_smoke.pyThe live smoke suite is intentionally small and read-only.
Maintainers release from a clean, synchronized main branch:
scripts/release patchThe helper bumps the version, commits and pushes it, then creates a GitHub Release. The release workflow builds the distributions and publishes them to PyPI through trusted publishing.
Variable | Default | Purpose |
|
| Upstream service |
|
| Request timeout, capped at 120 seconds |
|
| Local page-size ceiling |
Describe one IPCC sector code: name, level, parent, direct children.
Parents already include children; never sum a sector with its parent or children (double counting).
Inputs: sector_code (required). Returns: object
Explain reported actual, projection, policy estimate, and derived statuses.
Inputs: no named parameters. Returns: object
Describe schema, grain, keys, joins, reporting cycle, and caveats.
Inputs: table (required), version (required), database (required). Returns: object
Explain referenced objects, joins, filters, aggregations, and query risks.
Inputs: sql (required), max_rows. Returns: object
Curated national GHG inventory time series with the statistically correct variable.
country: ISO-style Discodata country code, e.g. 'HU', 'AT', 'EUA'. sector: 'total' or an IPCC sector code at any depth: '1', '1.A', '1.A.3' (discover codes via search_emission_sectors). Never sum a sector with its parent or children. accounting_scope: 'with_lulucf' or 'without_lulucf' (totals only). Avoids TREND/BASE_YEAR_AVG/PREV_SUBMISSION variants; sorted client-side by year.
Inputs: country (required), gas, sector, end_year, +2 more. Returns: object
Fetch one policy or measure with explicit quantification semantics.
Returns the full record plus a quantification block: status is 'reported' or 'not_reported'; ex-ante values by scope (total/esr/ eu_ets/lulucf) and target year, ex-post average if reported.
Inputs: country (required), measure_id (required). Returns: object
Preview provenance classification for a query without executing it.
Inputs: sql (required), max_rows. Returns: object
Return the documented and live-tested Discodata SQL capability matrix.
Inputs: no named parameters. Returns: object
List allowlisted EEA climate databases and available versions.
Inputs: no_cache. Returns: result
List bounded distinct values after validating the column against metadata.
Inputs: table (required), column (required), version (required), database (required), +1 more. Returns: object
Search the Policies and Measures catalogue (descriptive, not a ranking source).
country: PaMs country label, e.g. 'Hungary', 'Germany'. status: e.g. 'Implemented', 'Planned', 'Adopted', 'Expired'. sector/instrument_type/ responsible_entity/free_text are substring matches. Quantified effect fields are sparse; missing values mean not reported, not zero.
Inputs: sector, status, country, max_rows, +5 more. Returns: object
List tables in a database version.
Inputs: database (required), version. Returns: result
List version and revision aliases for an allowlisted database.
Inputs: database (required). Returns: result
Preview a small bounded set of rows with provenance.
Inputs: table (required), version (required), database (required), max_rows. Returns: object
Execute a locally validated and bounded SELECT, returning rows and provenance.
Inputs: sql (required), page, timeout, max_rows, +1 more. Returns: object
Find IPCC inventory sector codes by code prefix or name substring.
Returns sector_code, name, hierarchy level, and parent for each match, e.g. query 'transport' -> 1.A.3 and its subsectors.
Inputs: query (required), max_rows. Returns: object
Search table names, descriptions, columns, and column descriptions.
Inputs: text (required). Returns: result
Parse and validate one allowlisted, read-only, bounded SELECT query.
Inputs: sql (required), max_rows. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 18 tools
The SQL-related tools (validate_sql, explain_sql, query_sql, preview_rows, list_distinct_values) have overlapping purposes, though descriptions help distinguish them. get_emissions_series and query_sql both return data but serve different intents, and get_measure vs list_measures is clear.
Tool names follow a consistent verb_noun pattern: get_, list_, search_, describe_, validate_, explain_, query_, preview_. There are no mixed conventions or inconsistent styles.
18 tools is on the heavier side, largely due to 12 SQL-focused tools. The server's purpose is broad (emissions, measures, SQL exploration), but the count feels slightly over-optimized for coherence.
The tool set covers emissions data, sector metadata, PaMs catalogue, and SQL exploration. Missing update/delete operations are appropriate for a read-only data server. Core workflows are supported with no dead ends.
Eurostat MCP — wraps Eurostat Statistical Data API (no auth required)
Read-only electricity, gas, and weather data with structured provenance and units.
Carbon accounting platform. Query emission factors and create or edit draft emissions.
UN FAOSTAT global food & agriculture statistics over a local SQLite mirror, via MCP.
