org.georgiacivicdata/georgia-civic-data

Est-ce que org.georgiacivicdata/georgia-civic-data est sûr ?

Au dernier audit MCP Hub, le serveur MCP « org.georgiacivicdata/georgia-civic-data » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 13 outils

• aggregate≈ 830 tokens

  Compute a grouped aggregate over one topic — the aggregation-first path. `agg` is one of avg/sum/min/max/count/weighted_rate; `metric` is a metric column (DEFAULTS to the topic key_metric; ignored for count); `group_by` is a list of grain columns (year, FK codes like district_code or county_fips, or categoricals — see describe_dataset). `weighted_rate` computes a true population-weighted SUM(numerator)/SUM(denominator) for a rate key metric (when the contract declares the components) — prefer it over `avg` for a rate across multiple places/years, since `avg` means the per-row rates and ignores population. With `metric` set to a column the topic's `pooled_rates` lists (a zone's people per square mile), it pools that rate's own declared numerator and denominator (SUM(people) / SUM(land area)) over rows carrying both. Supports the same `filters` / `year` / `year_min`-`year_max` / `detail` as query_dataset, plus `order_by`+`order` for top-N (order_by 'value' for the aggregated column; NULL cells sort LAST in either direction). Returns one small row per group with `<metric>_<agg>` (or `row_count`) plus coverage diagnostics (input_rows / non-null counts) so suppression is visible; `aggregation_scope` flags whether rows are source-published at this grain or recomputed from a finer detail (prefer source-published — see the advisory). A `sum`/`weighted_rate` ACROSS a column the contract declares non_additive (overlapping rows, e.g. county rows that count one application in several counties) still returns, but carries a top-level `non_additive` block and a leading `non_additive_sum` advisory: that figure is NOT a total — group_by the column or use the published total row instead. Aggregates SKIP NULLs and NULL means SUPPRESSED not zero. No raw SQL: all identifiers are contract-allowlisted.

  Paramètres, retour & exemple (14)

  Paramètres

  • agg · string · optionnel
  • year · ? · optionnel
  • limit · ? · optionnel
  • order · string · optionnel
  • topic · string · requis
  • detail · ? · optionnel
  • metric · ? · optionnel
  • offset · integer · optionnel
  • filters · ? · optionnel
  • group_by · ? · optionnel
  • order_by · ? · optionnel
  • year_max · ? · optionnel
  • year_min · ? · optionnel
  • main_topic · string · optionnel

  Exemple d'appel

  {"name": "aggregate", "arguments": {"topic": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• describe_dataset≈ 645 tokens

  Full schema for one topic: every column (name/type/role/unit/value range/null-meaning), the exact `filters` list with enum values (read this before query_dataset — it is the authoritative set of filter keys), the FK→dimension join shape (`foreign_keys`), example queries, usage, limitations, null semantics, tags, and `schema_hash` (for cache/drift detection). The top-level `key_metric` names the single headline column most answers want; each column carries `key_metric_grain_contributor` (a grain axis the key metric is only comparable within — pin or group by it) and `metric_component` (numerator/denominator of a rate/average metric). `recommended_query` gives the safe default query shape (key metric + filters to pin + required single-selects) plus a `ranking` recipe for top/bottom-N asks; `filter_hints` lists paired filters; `non_additive` lists columns whose rows overlap (never sum across them; a metric entry names metric columns never to add together) and `value_implications` values that imply another column's value; `year_meaning`, when set, says what `year` labels when it is not when the figures were measured (never present that year as the figures' date); `pooled_rates` lists rates whose figure for several rows is SUM(numerator) / SUM(denominator) (aggregate agg='weighted_rate' with that metric), never an average of the rows' rates; each categorical filter carries `has_total` / `requires_single_value`. Pass `verbosity='schema'` for a much smaller payload that drops the prose (description/usage/limitations/example queries/column descriptions) but keeps every field needed to compose a correct query — use it when you only need the filter keys and enums; prefer the default 'full' before reporting conclusions (the limitations prose carries the caveats). On an unknown topic returns a self-describing error listing available topics + a 'did you mean' hint. `main_topic` defaults to 'education'; pass 'census' for Census topics or 'immigration' for immigration topics.

  Paramètres, retour & exemple (3)

  Paramètres

  • topic · string · requis
  • verbosity · string · optionnel
    'full' (default) or 'schema' (drops prose; keeps columns/filters/enums/key_metric/recommended_query).
  • main_topic · string · optionnel

  Exemple d'appel

  {"name": "describe_dataset", "arguments": {"topic": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• describe_dimension≈ 191 tokens

  Schema for one dimension (districts / schools / counties / demographics): the (possibly composite) primary key, the attribute columns a join attaches, the cross-dataset `link_keys` (e.g. districts.district_census_id → Census via the crosswalk — a 5-digit school-district code, NOT a county FIPS), and demographics `semantics` (within a category the values are mutually exclusive; `all` is the denominator). Read this before writing a link_query join.

  Paramètres, retour & exemple (1)

  Paramètres

  • name · string · requis

  Exemple d'appel

  {"name": "describe_dimension", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• distinct_values≈ 340 tokens

  List the distinct values of ONE filterable column of a topic — the fast way to learn valid filter values before query_dataset, especially for FREE categoricals and FK codes (district_code/school_code/county_fips/demographic) that carry no enum in describe_dataset (a wrong guess otherwise returns an empty page with no error). `column` must be a filterable column (see describe_dataset's `filters`). Optional `prefix` does a case-insensitive starts-with filter; `limit` caps results (default 50). Enum-bearing columns return their contract enum directly; others run a capped SELECT DISTINCT over the gold data. `truncated` flags when the list is capped.

  Paramètres, retour & exemple (6)

  Paramètres

  • limit · integer · optionnel
  • topic · string · requis
  • column · string · requis
  • detail · ? · optionnel
  • prefix · ? · optionnel
  • main_topic · string · optionnel

  Exemple d'appel

  {"name": "distinct_values", "arguments": {"topic": "texte", "column": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_contract≈ 210 tokens

  Return the authoritative ODCS v3.2 data contract for a topic (kind='topic') or a dimension (kind='dimension') so you can consume the machine-readable schema without cloning the repo. fmt='yaml' (default) returns the document verbatim as text; fmt='json' returns it parsed. Only approved topics and loaded dimensions expose a contract.

  Paramètres, retour & exemple (4)

  Paramètres

  • fmt · string · optionnel
  • kind · string · optionnel
  • name · string · requis
  • main_topic · string · optionnel

  Exemple d'appel

  {"name": "get_contract", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_dimension≈ 202 tokens

  Paginated read of a dimension table — the label lookups (district names, school names, county names, demographic labels). Rows are ordered by the dimension's primary key so paging is stable. Use describe_dimension for the schema and link keys. Small page defaults; `truncated` + a `bulk_export` pointer signal when to pull the full table elsewhere.

  Paramètres, retour & exemple (3)

  Paramètres

  • name · string · requis
  • limit · ? · optionnel
  • offset · integer · optionnel

  Exemple d'appel

  {"name": "get_dimension", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• link_query≈ 351 tokens

  Run a cross-dataset / cross-topic analytical SQL query that the per-topic query_dataset filters can't express — e.g. join education, Census, or immigration facts to a dimension (or another dataset) on shared geography (immigration and Census county topics share county_fips directly). READ-ONLY, SANDBOXED DuckDB: one SELECT (or WITH … SELECT); no DDL/DML/COPY/ATTACH/INSTALL/PRAGMA/SET/CALL; you may only read_parquet() the curated gold paths returned by link_tables (call it first and paste the snippets) — querying a file path directly is rejected. Joins use the keys from describe_dimension's link_keys (districts.district_census_id bridges to Census via the crosswalk — it is a school-district code, not a county FIPS, so a district is not 1:1 with a county). Results are row- and byte-capped and time-limited; `truncated` flags when capped — add aggregation or a tighter WHERE rather than dumping rows. NULL means suppressed, not zero. On a violation you get a self-describing error naming the offending token/path.

  Paramètres, retour & exemple (2)

  Paramètres

  • sql · string · requis
  • limit · ? · optionnel

  Exemple d'appel

  {"name": "link_query", "arguments": {"sql": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• link_tables≈ 274 tokens

  List the tables link_query can read (curated gold paths only) and the join keys that bridge facts → dimensions → Census geography. Call this BEFORE writing a link_query. Two-tier to stay context-cheap: with NO arguments it returns a LEAN index — every table's name, grain, detail levels, default `read_parquet(...)` snippet, and join keys (enough to pick tables and write a single-detail join). To get every column and a snippet per detail level for the few tables you actually need, call again with `tables=["<name>", ...]` (a `name` from the index, e.g. 'education/gosa/attendance' or 'attendance', or a dimension like 'districts'). Paste the `read_parquet(...)` snippets verbatim into your SQL — they are exactly what the sandbox accepts.

  Paramètres, retour & exemple (1)

  Paramètres

  • tables · ? · optionnel

  Exemple d'appel

  {"name": "link_tables", "arguments": {"tables": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_datasets≈ 276 tokens

  Enumerate every approved Georgia dataset (topic) and the shared dimensions. Each topic entry is a LEAN summary — name/keys, year coverage (year_min/year_max + year_gaps), detail levels + default detail, a has_demographic flag (false = no demographic axis, so there is no all-students demographic row to filter), tags, contract version, and a one-line description — enough to pick a topic; call describe_dataset for its full schema (columns, filters, grain, source, example queries). Each dimension entry carries its primary key, attribute columns, and (for districts) cross-dataset link keys. A top-level `license` object gives the terms the data is served under (CC BY 4.0, with attribution). Call this first to learn what exists — but for a NAMED task (you already know roughly the topic), prefer search_datasets, which returns far fewer bytes than this full catalog.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_datasets", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• lookup_school_zone≈ 696 tokens

  Which Georgia public school attendance zones (elementary, middle, high) contain a place, or (attendance_rules=true) how attendance zones work in Georgia. Give exactly one of: lat + lon; an address (geocoded by the U.S. Census Geocoder); a 2020 census tract_geoid (returns every zone covering the tract with the share of its 2020 population in each, or, when none does, a coverage_reason saying why); or attendance_rules=true with no place. Optional grade (pk, k, 01-12) and year. Returns the district, the zoned schools with labels and provenance (method, accuracy_class, positional_rmse_m, boundary_vintage, currency_status, currency_note, source_url), a level_status per school level, a coverage_status (zoned, gap — some level has no zone there — one_school_per_grade, not_available — the district publishes no zones at some level — with the reason, not_zoned — no zone assigns the grade asked, i.e. pre-K), a currency_warning when a zone's source predates an adopted change that could not be applied (it quotes what changed, by level), an overlap_warning when two schools' zones cover the point for the same grades (it names them, by level), the point's tract and county, and a geojson_url per zone — never the polygons themselves. Zones are reconstructed from published sources of varying currency and are NOT an official enrollment determination: always tell the user to confirm with the district. The zoned school is the default assignment (the result's assignment_note says so). attendance_rules=true returns instead who draws zones and the main ways a student attends a public school other than the zoned one, with the statute or rule behind each: use it when a user asks how zones work or whether a child must attend the zoned school. A dated summary, not legal advice; lang="es" gives it in Spanish.

  Paramètres, retour & exemple (8)

  Paramètres

  • lat · ? · optionnel
  • lon · ? · optionnel
  • lang · string · optionnel
  • year · ? · optionnel
  • grade · ? · optionnel
  • address · ? · optionnel
  • tract_geoid · ? · optionnel
  • attendance_rules · boolean · optionnel

  Exemple d'appel

  {"name": "lookup_school_zone", "arguments": {"lat": "texte", "lon": "texte", "lang": "texte", "year": "texte", "grade": "texte", "address": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• query_dataset≈ 1025 tokens

  Query one topic's gold facts with dimension labels joined in (the district/school/county/demographic names come back on every row). `filters` is a dict of column → value or list-of-values: FK codes (district_code, school_code, county_fips, demographic) and any categorical column — see describe_dataset's `filters` for the exact keys and enum values. Use `year` (exact) OR `year_min`/`year_max` (range), never both. `detail` picks the grain (default is the finest available). Returns `rows` plus a `columns` descriptor array (type/role/unit/null-meaning, and `is_key_metric` flagging the headline column) so you interpret values and NULLs correctly — NULL usually means SUPPRESSED, not zero (see null_semantics). The top-level `key_metric` echoes which column is the answer. Use `columns` to project a subset, `include_labels=false` to skip the joined name columns (codes only), and `order_by`+`order` for server-side top-N instead of over-fetching. Pages are small (default 100, max 500); when `truncated` is true a `bulk_export` block points at the REST CSV/Parquet endpoint and the source path for the full pull — do not loop pagination to dump a table. A bad filter returns a self-describing error listing the valid keys/values.

  Paramètres, retour & exemple (13)

  Paramètres

  • year · ? · optionnel
    Exact year. Use this OR year_min/max.
  • limit · ? · optionnel
    Page size (default 100, max 500).
  • order · string · optionnel
    Sort direction for order_by: 'asc' or 'desc'.
  • topic · string · requis
    Topic name, e.g. 'act_scores'.
  • detail · ? · optionnel
    Grain (e.g. schools/districts/states); default finest.
  • offset · integer · optionnel
    Row offset for paging (>= 0).
  • columns · ? · optionnel
    Project only these output columns (fact columns + joined label columns). Smaller pages / fewer column reads. Omit for all columns.
  • filters · ? · optionnel
    Column → value (or list of values) filters. Keys are FK columns (district_code, school_code, county_fips, demographic) and categorical columns; read describe_dataset's `filters` for the exact keys and enum values FIRST. A value list is a union (OR); multiple keys AND together. A wrong key/value returns a self-describing error listing the valid ones.
  • order_by · ? · optionnel
    Order by one fact column or joined label column (for server-side top-N). Default order is the row grain. NULL (suppressed) cells sort LAST in either direction, so a metric top-N is never polluted by suppressed rows.
  • year_max · ? · optionnel
    Inclusive upper year bound (range).
  • year_min · ? · optionnel
    Inclusive lower year bound (range).
  • main_topic · string · optionnel
    Main topic: 'education', 'census', or 'immigration'.
  • include_labels · boolean · optionnel
    Join district/school/county/demographic name columns (default true); false = codes only (faster, leaner).

  Exemple d'appel

  {"name": "query_dataset", "arguments": {"topic": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• resolve_entity≈ 410 tokens

  Resolve a place or demographic NAME or CODE to its stable keys + labels — the right way to turn 'Atlanta Public Schools' / 'Fulton' / a raw code into the district_code / school_code / county_fips / demographic to filter by (a wrong code guess otherwise returns an empty query_dataset page). `kind` is district / school / county / demographic ('Fulton' as kind='county' → the county; as kind='district' → the school district — they are different things). Fuzzy-matches and ranks candidates, flags `ambiguous` when several tie, and reads only the small dimension table (no fact scan). A real Georgia place is never matched to a different one: a consolidated city returns its county (matched_on=consolidated_city: 'Columbus' -> Muscogee), another city asked as a county returns the county it lies in flagged ambiguous, and a one-letter misspelling returns matched_on=typo. A city school system answers to any common shape of its name (matched_on=city_system: 'Decatur City' / 'Decatur Public Schools' -> City Schools Of Decatur), and a county's system to its place name (matched_on=county_system: 'Gwinnett Public Schools' / 'Cobb Schools' -> the county's district). Read `place_note` and tell the user when it is present.

  Paramètres, retour & exemple (3)

  Paramètres

  • kind · string · requis
  • limit · integer · optionnel
  • query · string · requis

  Exemple d'appel

  {"name": "resolve_entity", "arguments": {"kind": "texte", "query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_datasets≈ 216 tokens

  Keyword search over the catalog metadata (topic names, descriptions, tags, AND column names/descriptions) — the discovery entry point when you don't know the exact topic name. Returns lean topic summaries per hit with a relevance score and which fields matched, plus a `dimension_matches` list when the query also hits a dimension (e.g. 'district'). Most acronyms work; the short ones `ap`/`el`/`ib` are recognized. Follow up with describe_dataset. `limit` caps results (default 20, max 100).

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
  • query · string · requis

  Exemple d'appel

  {"name": "search_datasets", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.georgiacivicdata.org/mcp/