
André MCP server
Which MCP servers are André's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-26
- Registry namevote.andre/electionsverified in the MCP registry
The registry name sits under andre.vote. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-26
- Tools11
- Server calls itselfandré
- Server version1.26.0
- Protocol version2025-06-18
On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 756 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 2 of the 7 days it takes to judge reliability.
Once connected
- create_data_table change data without a sign-in: anyone with the address can call them.
- Parameters are untyped or undescribed in 11 of 11 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer840 ms
- Space in an agent's context≈ 4,502 tokensthe definitions of all its tools (11), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results11 of 11 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 11 of 11
Worth a look
- Tools that change data, on a server that answers without a sign-in: create_data_table
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
query_electionsRequête 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…
query_adminRequête les divisions administratives françaises. Actions : search_commune, get_commune, search_postal, list_epci, get_epci, list_cantons, list_departements, list_regions.
query_elusRequête les élus de la République française (base BRÉF). Actions : search_elu, list_mandate_types, list_elus.
query_sociodemRequête 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.
query_dlpRequête 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…
generate_mapGénère 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), 'nuance' (score d'une nuance), 'abstention'…
simulate_fusionsSimule 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.
export_dataExporte des données électorales vers un fichier téléchargeable (CSV, JSON, TSV). Deux modes : data (contenu inline) ou source_path (chemin vers fichier existant).
visualizeCrée 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…
create_data_tableCrée un tableau de données formaté à partir de données structurées. Utile pour présenter des résultats calculés ou combinés. Retourne un tableau texte formaté.
query_sqlExécute 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…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"elections": {
"type": "http",
"url": "https://mcp.andre.vote/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http andre https://mcp.andre.vote/mcpclaude.ai, ChatGPT and other clients: add https://mcp.andre.vote/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.