André — Analyse électorale française
Résultats des élections françaises 1999-2026 par bureau de vote, socio-démo INSEE et cartes.
我該用這個嗎
品質與安全性
發現項目（1）
- LOWTool 'generate_map' description lacks action verb在 generate_map 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"elections": {
"url": "https://mcp.andre.vote/mcp"
}
}
}遠端端點
https://mcp.andre.vote/mcpstreamable-http它能做什麼
工具清單
工具（11）
🟢query_elections(action, election_id, commune_code, departement_code, region_code, ...)
Requête les données électorales françaises (1999-2026). Niveaux territoriaux : NATIONAL (aucun filtre), RÉGIONAL (region_code), DÉPARTEMENTAL (departement_code), COMMUNAL (commune_code). Actions de base : list_elections, query_results, list_bureaux, query_bureau, query_by_bureau, rank_bureaux, list_circonscriptions, query_circonscription, list_cantons, query_canton, search_candidate, query_candidatures, etc. Actions « panel » (1 appel = analyse complète, évite les boucles) : - compare_elections : compare deux scrutins pour un territoire (election_id + compare_to_election + commune_code|departement_code, candidate_name optionnel). - query_all_circonscriptions : vainqueur de CHAQUE circonscription d'un territoire en un appel (election_id + commune_code|departement_code, législatives uniquement). - vote_reserve : score d'une famille + abstention par bureau de vote sur les scrutins récents comparables (commune_code + famille). - select_communes : sélectionne/classe des communes par critères géo + population + électoraux (region_code/departement_code/epci/commune_codes, population_min/max, commune_metric, condition, sort_by, limit, order ; commune_metric/condition nécessitent election_id). commune_metric accepte PLUSIEURS métriques séparées par des virgules — une colonne chacune, en un seul appel ; condition et sort_by portent alors sur la première. - cross_election_panel : évolution d'un sujet (famille ou nuance_code) par commune sur N scrutins (elections=ids séparés par des virgules + scope optionnel commune_code/departement_code/region_code/commune_codes ; SANS scope = national, panel complet en data_file). Renvoie aussi « ensemble » : score du périmètre entier par scrutin + delta, pondéré par les exprimés — ne pas boucler par département. famille et nuance_code acceptent PLUSIEURS sujets séparés par des virgules ('Gauche,Droite') : tous en un appel, agrégats dans « ensembles ». group_by='region'| 'departement' ajoute un agrégat pondéré PAR MAILLE dans le même appel — ne jamais boucler un appel par région. - bureau_breakdown : pivot par bureau (top_n nuances/blocs + participation, with_sociodem optionnel) pour commune_code + election_id.
輸入結構描述
{
"type": "object",
"properties": {
"action": {
"title": "Action",
"type": "string"
},
"election_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Election Id"
},
"commune_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Commune Code"
},
"departement_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Departement Code"
},
"region_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Region Code"
},
"bureau_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Bureau Id"
},
"bureau_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Bureau Code"
},
"candidate_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Candidate Name"
},
"family_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Family Name"
},
"by_family": {
"default": false,
"title": "By Family",
"type": "boolean"
},
"rank_metric": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rank Metric"
},
"order": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Order"
},
"limit": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Limit"
},
"offset": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Offset"
},
"use_ferd_coding": {
"default": false,
"title": "Use Ferd Coding",
"type": "boolean"
},
"nuance_level": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Nuance Level"
},
"circonscription_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Circonscription Code"
},
"canton_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Canton Code"
},
"candidate_query": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Candidate Query"
},
"candidate_search": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Candidate Search"
},
"list_search": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "List Search"
},
"nuance_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Nuance Code"
},
"scrutin_type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Scrutin Type"
},
"tour": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Tour"
},
"compare_to_election": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Compare To Election"
},
"famille": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Famille"
},
"elections": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Elections"
},
"commune_codes": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Commune Codes"
},
"epci": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Epci"
},
"population_min": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Population Min"
},
"population_max": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Population Max"
},
"commune_metric": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Commune Metric"
},
"group_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Group By"
},
"condition": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Condition"
},
"sort_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Sort By"
},
"top_n": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Top N"
},
"with_sociodem": {
"default": false,
"title": "With Sociodem",
"type": "boolean"
}
},
"required": [
"action"
],
"title": "query_electionsArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "query_electionsOutput"
}🟢query_admin(action, search_term, commune_code, postal_code, departement_code, ...)
Requête les divisions administratives françaises. Actions : search_commune, get_commune, search_postal, list_epci, get_epci, list_cantons, list_departements, list_regions.
輸入結構描述
{
"type": "object",
"properties": {
"action": {
"title": "Action",
"type": "string"
},
"search_term": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Search Term"
},
"commune_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Commune Code"
},
"postal_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Postal Code"
},
"departement_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Departement Code"
},
"epci_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Epci Code"
}
},
"required": [
"action"
],
"title": "query_adminArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "query_adminOutput"
}🟢query_elus(action, search_term, mandate_type, departement_code)
Requête les élus de la République française (base BRÉF). Actions : search_elu, list_mandate_types, list_elus.
輸入結構描述
{
"type": "object",
"properties": {
"action": {
"title": "Action",
"type": "string"
},
"search_term": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Search Term"
},
"mandate_type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Mandate Type"
},
"departement_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Departement Code"
}
},
"required": [
"action"
],
"title": "query_elusArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "query_elusOutput"
}🟢query_sociodem(action, commune_code, variable, commune_codes, order)
Requête les données socio-démographiques au niveau bureau de vote. Données INSEE RP 2022 + Filosofi 2021, interpolées IRIS→BDV. Actions : list_variables, profile, indices, rank, compare.
輸入結構描述
{
"type": "object",
"properties": {
"action": {
"title": "Action",
"type": "string"
},
"commune_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Commune Code"
},
"variable": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Variable"
},
"commune_codes": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Commune Codes"
},
"order": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Order"
}
},
"required": [
"action"
],
"title": "query_sociodemArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "query_sociodemOutput"
}🟢query_dlp(action, commune_code, departement_code, classe, sexe, ...)
Requête les données DLP (composition sociale des candidats municipaux 2020). ~546 000 candidats dans ~10 000 communes (≥1 000 hab.). Classes : CDOM (dominant), CMOY (moyen), CSUB (subalterne), RET (retraité), AUTRES. Actions : summary, composition, parite, listes, candidats, professions, sortants.
輸入結構描述
{
"type": "object",
"properties": {
"action": {
"title": "Action",
"type": "string"
},
"commune_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Commune Code"
},
"departement_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Departement Code"
},
"classe": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Classe"
},
"sexe": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Sexe"
},
"tetes_only": {
"default": false,
"title": "Tetes Only",
"type": "boolean"
},
"sortants_only": {
"default": false,
"title": "Sortants Only",
"type": "boolean"
},
"search": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Search"
}
},
"required": [
"action"
],
"title": "query_dlpArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "query_dlpOutput"
}⚪generate_map(election_id, metric, geography, department, commune, ...)
Génère une carte électorale (PNG) pour une élection. Paramètres : - election_id : identifiant élection (ex: '2024_legi_t1', '2020_muni_t2') - metric : 'family' (famille politique en tête) ou 'nuance' (score d'une nuance) - geography : 'bv' (bureau de vote, défaut) ou 'commune' (carte nationale) - department : code département (ex: '13'). Requis pour geography='bv' sauf si commune fourni. - commune : code commune (ex: '13055' pour Marseille). Centre la carte sur cette commune. - nuance : code nuance quand metric='nuance' (ex: 'RN', 'LFI', 'ENS') - region : code région pour geography='commune' (ex: '93' pour PACA) Exemples : - Carte par famille, Bouches-du-Rhône : election_id='2024_legi_t1', department='13' - Carte score RN, Marseille : election_id='2024_legi_t1', commune='13055', metric='nuance', nuance='RN' - Carte nationale : election_id='2024_euro_t1', geography='commune'
輸入結構描述
{
"type": "object",
"properties": {
"election_id": {
"title": "Election Id",
"type": "string"
},
"metric": {
"default": "family",
"title": "Metric",
"type": "string"
},
"geography": {
"default": "bv",
"title": "Geography",
"type": "string"
},
"department": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Department"
},
"commune": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Commune"
},
"region": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Region"
},
"nuance": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Nuance"
},
"circonscription": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Circonscription"
},
"canton": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Canton"
}
},
"required": [
"election_id"
],
"title": "generate_mapArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "generate_mapOutput"
}🟢simulate_fusions(action, election_id, commune_code, report_rate)
Simule les scénarios de fusion de listes municipales entre T1 et T2. Actions : 'status' (classer les listes après T1), 'simulate' (projections T2). Uniquement pour les élections municipales.
輸入結構描述
{
"type": "object",
"properties": {
"action": {
"title": "Action",
"type": "string"
},
"election_id": {
"title": "Election Id",
"type": "string"
},
"commune_code": {
"title": "Commune Code",
"type": "string"
},
"report_rate": {
"default": 0.75,
"title": "Report Rate",
"type": "number"
}
},
"required": [
"action",
"election_id",
"commune_code"
],
"title": "simulate_fusionsArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "simulate_fusionsOutput"
}⚪export_data(filename, file_format, data, source_path)
Exporte des données électorales vers un fichier téléchargeable (CSV, JSON, TSV). Deux modes : data (contenu inline) ou source_path (chemin vers fichier existant).
輸入結構描述
{
"type": "object",
"properties": {
"filename": {
"title": "Filename",
"type": "string"
},
"file_format": {
"default": "csv",
"title": "File Format",
"type": "string"
},
"data": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Data"
},
"source_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Source Path"
}
},
"required": [
"filename"
],
"title": "export_dataArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "export_dataOutput"
}⚪visualize(chart_type, data, data_file, spec, x, ...)
Crée une visualisation Plotly (retourne le spec JSON). Deux modes : - Spec libre : fournir 'spec' (dict Plotly complet {data, layout}) - Assisté : fournir chart_type + data + mappings Types supportés : bar, line, scatter, histogram, box, violin, heatmap, treemap, grouped_bar, stacked_bar, dumbbell, diverging_bar, dual_axis (x + y + y2), sankey (source + target + values), hemicycle (x=groupe, y=sièges), ternary (a + b + c = trois parts). Paramètres transversaux : subtitle (sous-titre technique), reference_line ({value, label, orientation}) pour un seuil/référence.
輸入結構描述
{
"type": "object",
"properties": {
"chart_type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Chart Type"
},
"data": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Data"
},
"data_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Data File"
},
"spec": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Spec"
},
"x": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "X"
},
"y": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Y"
},
"color": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Color"
},
"title": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Title"
},
"subtitle": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Subtitle"
},
"y2": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Y2"
},
"source": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Source"
},
"target": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Target"
},
"values": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Values"
},
"z": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Z"
},
"path": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Path"
},
"a": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "A"
},
"b": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "B"
},
"c": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "C"
},
"size": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Size"
},
"reference_line": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Reference Line"
}
},
"title": "visualizeArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "visualizeOutput"
}🟡create_data_table(title, columns, rows, description)
Crée un tableau de données formaté à partir de données structurées. Utile pour présenter des résultats calculés ou combinés. Retourne un tableau texte formaté.
輸入結構描述
{
"type": "object",
"properties": {
"title": {
"title": "Title",
"type": "string"
},
"columns": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Columns",
"type": "array"
},
"rows": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Rows",
"type": "array"
},
"description": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Description"
}
},
"required": [
"title",
"columns",
"rows"
],
"title": "create_data_tableArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "create_data_tableOutput"
}🟢query_sql(query)
Exécute une requête SQL directe sur la base DuckDB (read-only). Tables principales : - general_results : résultats généraux par bureau de vote - candidats_results : résultats par candidat par bureau de vote - elections_disponibles : liste des élections (id_election, nb_bureaux, total_inscrits) - candidats_avec_nuances : candidats avec famille politique (si nuances enrichies) - resultats_par_famille : résultats agrégés par famille politique - communes, epci, departements, regions : divisions administratives - bv_sociodemographique : données socio-démo par bureau de vote ATTENTION — colonnes de general_results (noms avec espaces, à quoter) : id_election, id_brut_miom, "Code du département", "Code de la commune" (SANS préfixe dept, ex: '055' pour Marseille), "Libellé de la commune", Inscrits, Abstentions, Votants, Blancs, Nuls, Exprimés. PRÉFÉRER query_elections pour les analyses standard — query_sql est pour les requêtes ad hoc avancées. Exemple : SELECT id_election, ROUND(100.0 * SUM(Abstentions) / NULLIF(SUM(Inscrits), 0), 1) as abstention_pct FROM general_results WHERE "Code du département" = '13' AND "Code de la commune" = '055' GROUP BY id_election ORDER BY id_election DESC LIMIT 5
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
}
},
"required": [
"query"
],
"title": "query_sqlArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "query_sqlOutput"
}社群
證據