Skip to main content
Glama
Hug0x0

mcp-reunion

reunion_search_joconde_collections

Search the Joconde national database for artworks and objects from La Réunion museum collections. Retrieve references, titles, authors, domains, and more for cultural research.

Instructions

Search the Joconde national database extract restricted to La Réunion museum collections. Joconde is the official catalog of artworks and objects held by French museums. Returns reference, title, author, domain (painting, sculpture, photography, ethnography, etc.), denomination, materials/techniques, period and millesime of creation, inventory number, museum, Muséofile code, description, location within museum, city. Useful for cultural research, art history, exhibition curation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryNoFree-text search across title, author, description, denomination
museumNoMuseum name prefix match (e.g. "Musée Léon Dierx", "Stella Matutina")
domainNoDomain prefix match. Examples: "peinture", "sculpture", "photographie", "ethnographie", "estampe", "dessin"
limitNoMax items to return (1-100, default 25)

Implementation Reference

  • The registerCultureTools function registers the 'reunion_search_joconde_collections' tool with the MCP server (line 44-86), along with the server.tool() call, schema definitions, and handler logic.
    export function registerCultureTools(server: McpServer): void {
      server.tool(
        'reunion_list_museums',
        'List museums in La Réunion holding the official "Musée de France" designation (granted by the Ministry of Culture under the 2002 law). This designation guarantees scientific standards, public access, and inalienability of collections. Returns Muséofile ID, official name, commune, full address, postal code, phone, URL, designation decree date, lat/lon. Use reunion_get_museum_attendance for visitor statistics, reunion_search_joconde_collections for artwork records.',
        {},
        async () => {
          try {
            const data = await client.getRecords<RecordObject>(DATASET_MUSEUMS, { limit: 50 });
            return jsonResult({
              total_museums: data.total_count,
              museums: data.results.map((row) => ({
                museofile_id: pickString(row, ['identifiant_museofile']),
                name: pickString(row, ['nom_officiel_du_musee']),
                commune: pickString(row, ['commune']),
                address: pickString(row, ['adresse']),
                postal_code: pickString(row, ['code_postal']),
                phone: pickString(row, ['telephone']),
                url: pickString(row, ['url']),
                designation_date: pickString(row, ['date_arrete_attribution_appellation']),
                lat: pickNumber(row, ['latitude']),
                lon: pickNumber(row, ['longitude']),
              })),
            });
          } catch (error) {
            return errorResult(error instanceof Error ? error.message : 'Failed to list museums');
          }
        }
      );
    
      server.tool(
        'reunion_search_joconde_collections',
        'Search the Joconde national database extract restricted to La Réunion museum collections. Joconde is the official catalog of artworks and objects held by French museums. Returns reference, title, author, domain (painting, sculpture, photography, ethnography, etc.), denomination, materials/techniques, period and millesime of creation, inventory number, museum, Muséofile code, description, location within museum, city. Useful for cultural research, art history, exhibition curation.',
        {
          query: z.string().optional().describe('Free-text search across title, author, description, denomination'),
          museum: z.string().optional().describe('Museum name prefix match (e.g. "Musée Léon Dierx", "Stella Matutina")'),
          domain: z.string().optional().describe('Domain prefix match. Examples: "peinture", "sculpture", "photographie", "ethnographie", "estampe", "dessin"'),
          limit: z.number().int().min(1).max(100).default(25).describe('Max items to return (1-100, default 25)'),
        },
        async ({ query, museum, domain, limit }) => {
          try {
            const data = await client.getRecords<RecordObject>(DATASET_JOCONDE, {
              where: buildWhere([
                query ? `search(${quote(query)})` : undefined,
                museum ? `nom_officiel_musee LIKE ${quote(`${museum}%`)}` : undefined,
                domain ? `domaine LIKE ${quote(`${domain}%`)}` : undefined,
              ]),
              limit,
            });
            return jsonResult({
              total_items: data.total_count,
              items: data.results.map((row) => ({
                reference: pickString(row, ['reference']),
                title: pickString(row, ['titre']),
                author: pickString(row, ['auteur']),
                domain: pickString(row, ['domaine']),
                denomination: pickString(row, ['denomination']),
                materials: pickString(row, ['materiaux_techniques']),
                period: pickString(row, ['periode_de_creation']),
                millesime: pickString(row, ['millesime_de_creation']),
                inventory_number: pickString(row, ['numero_inventaire']),
                museum: pickString(row, ['nom_officiel_musee']),
                museofile_code: pickString(row, ['code_museofile']),
                description: pickString(row, ['description']),
                location: pickString(row, ['localisation']),
                city: pickString(row, ['ville']),
              })),
            });
          } catch (error) {
            return errorResult(error instanceof Error ? error.message : 'Failed to search Joconde');
          }
        }
      );
  • The actual handler function for 'reunion_search_joconde_collections' – an async function that accepts query, museum, domain, and limit parameters, queries the 'base-joconde-extraitculture' dataset via the ReunionClient, and returns structured results with fields like reference, title, author, domain, etc.
      async ({ query, museum, domain, limit }) => {
        try {
          const data = await client.getRecords<RecordObject>(DATASET_JOCONDE, {
            where: buildWhere([
              query ? `search(${quote(query)})` : undefined,
              museum ? `nom_officiel_musee LIKE ${quote(`${museum}%`)}` : undefined,
              domain ? `domaine LIKE ${quote(`${domain}%`)}` : undefined,
            ]),
            limit,
          });
          return jsonResult({
            total_items: data.total_count,
            items: data.results.map((row) => ({
              reference: pickString(row, ['reference']),
              title: pickString(row, ['titre']),
              author: pickString(row, ['auteur']),
              domain: pickString(row, ['domaine']),
              denomination: pickString(row, ['denomination']),
              materials: pickString(row, ['materiaux_techniques']),
              period: pickString(row, ['periode_de_creation']),
              millesime: pickString(row, ['millesime_de_creation']),
              inventory_number: pickString(row, ['numero_inventaire']),
              museum: pickString(row, ['nom_officiel_musee']),
              museofile_code: pickString(row, ['code_museofile']),
              description: pickString(row, ['description']),
              location: pickString(row, ['localisation']),
              city: pickString(row, ['ville']),
            })),
          });
        } catch (error) {
          return errorResult(error instanceof Error ? error.message : 'Failed to search Joconde');
        }
      }
    );
  • Zod schema definitions for input validation: query (optional string), museum (optional string), domain (optional string), limit (integer 1-100, default 25).
    {
      query: z.string().optional().describe('Free-text search across title, author, description, denomination'),
      museum: z.string().optional().describe('Museum name prefix match (e.g. "Musée Léon Dierx", "Stella Matutina")'),
      domain: z.string().optional().describe('Domain prefix match. Examples: "peinture", "sculpture", "photographie", "ethnographie", "estampe", "dessin"'),
      limit: z.number().int().min(1).max(100).default(25).describe('Max items to return (1-100, default 25)'),
    },
  • Import of registerCultureTools from culture.ts.
    import { registerCultureTools } from './culture.js';
  • Invocation of registerCultureTools(server) within registerAllTools.
    registerCultureTools(server);
  • Dataset constant DATASET_JOCONDE = 'base-joconde-extraitculture' used by the handler.
    const DATASET_JOCONDE = 'base-joconde-extraitculture';
  • The buildWhere helper used to construct the ODSQL WHERE clause from optional search conditions.
    export function buildWhere(
      conditions: Array<string | undefined | null | false>
    ): string | undefined {
      const valid = conditions.filter((condition): condition is string => Boolean(condition));
      return valid.length > 0 ? valid.join(' AND ') : undefined;
    }
  • The quote helper used to safely quote string literals for ODSQL queries.
    export function quote(value: string): string {
      return `'${escapeOdSqlString(value)}'`;
    }
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry behavioral disclosure. It does not mention rate limits, authentication, side effects, or pagination behavior. Only the return structure is described, leaving important behavioral traits unaddressed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences and efficiently conveys purpose, return fields, and use cases. It is front-loaded but could be slightly more structured, but overall concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the 4 parameters, no required fields, complete schema descriptions, and no output schema, the description provides adequate context about what the tool does and returns. It does not cover errors or limitations, but is complete enough for typical use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage with descriptions for all 4 parameters. The description adds value by listing returned fields and giving examples for domain, which aids understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches the Joconde national database extract restricted to La Réunion museum collections, specifies the fields returned, and provides use cases. This distinguishes it from sibling tools like 'reunion_search_catalog', which are broader.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for cultural research and art history related to Réunion museum collections, but does not explicitly state when to use this tool versus alternatives. No exclusion criteria or comparisons are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Hug0x0/mcp-reunion'

If you have feedback or need assistance with the MCP directory API, please join our Discord server