Skip to main content
Glama
Hug0x0

mcp-reunion

reunion_list_coworking_spaces

Retrieve coworking spaces and shared offices in La Réunion by commune. Returns contact details and location for remote work.

Instructions

List coworking spaces and shared offices in La Réunion (tiers-lieux numériques, espaces partagés, fab labs sometimes). Returns name, type, website, coarse location (zone), full address, email, phone, dataset page URL. Useful for remote workers, freelancers, business travelers needing flexible workspace.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
communeNoCoarse-location prefix match (typically a region or commune name like "Saint-Denis", "Saint-Pierre", "Le Tampon")
limitNoMax spaces to return (1-100, default 50)

Implementation Reference

  • Imports and constants used by the tool, including the DATASET_COWORKING dataset identifier 'espace-de-coworkings-sur-l-ile-de-la-reunion' and helper utilities like client, buildWhere, jsonResult, errorResult, pickString, quote.
    // src/modules/economy.ts
    
    import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
    import { z } from 'zod';
    import { client } from '../client.js';
    import { RecordObject } from '../types.js';
    import { buildWhere, errorResult, jsonResult, pickNumber, pickString, quote } from '../utils/helpers.js';
    
    const DATASET_SIRENE = 'base-sirene-v3-lareunion';
    const DATASET_CPI = 'insee-indices-des-prix-a-la-consommation-a-la-reunion-valeurs-mensuelles';
    const DATASET_FEDER = 'liste_des_operations_31';
    const DATASET_COWORKING = 'espace-de-coworkings-sur-l-ile-de-la-reunion';
    const DATASET_INCOME_IRIS = 'revenus-declares-pauvrete-et-niveau-de-vie-en-2015-irispublic';
  • The function signature registerEconomyTools(server: McpServer) that registers all economy tools, including reunion_list_coworking_spaces.
    export function registerEconomyTools(server: McpServer): void {
  • The exact tool handler implementation for 'reunion_list_coworking_spaces'. It accepts optional 'commune' (coarse location prefix filter) and 'limit' (1-100, default 50) parameters. Calls client.getRecords on the DATASET_COWORKING dataset with an ODSQL WHERE clause filtering by coarse_location, then maps results to return name, type, website, coarse_location, address, email, phone, and page_url.
    server.tool(
      'reunion_list_coworking_spaces',
      'List coworking spaces and shared offices in La Réunion (tiers-lieux numériques, espaces partagés, fab labs sometimes). Returns name, type, website, coarse location (zone), full address, email, phone, dataset page URL. Useful for remote workers, freelancers, business travelers needing flexible workspace.',
      {
        commune: z.string().optional().describe('Coarse-location prefix match (typically a region or commune name like "Saint-Denis", "Saint-Pierre", "Le Tampon")'),
        limit: z.number().int().min(1).max(100).default(50).describe('Max spaces to return (1-100, default 50)'),
      },
      async ({ commune, limit }) => {
        try {
          const data = await client.getRecords<RecordObject>(DATASET_COWORKING, {
            where: buildWhere([commune ? `coarse_location LIKE ${quote(`${commune}%`)}` : undefined]),
            limit,
          });
          return jsonResult({
            total_spaces: data.total_count,
            spaces: data.results.map((row) => ({
              name: pickString(row, ['name']),
              type: pickString(row, ['type']),
              website: pickString(row, ['website']),
              coarse_location: pickString(row, ['coarse_location']),
              address: pickString(row, ['address']),
              email: pickString(row, ['email']),
              phone: pickString(row, ['phone']),
              page_url: pickString(row, ['page_url']),
            })),
          });
        } catch (error) {
          return errorResult(error instanceof Error ? error.message : 'Failed to list coworking spaces');
        }
      }
    );
  • Zod schema for the tool's input parameters: commune (optional string, coarse-location prefix match) and limit (optional integer 1-100, default 50).
    {
      commune: z.string().optional().describe('Coarse-location prefix match (typically a region or commune name like "Saint-Denis", "Saint-Pierre", "Le Tampon")'),
      limit: z.number().int().min(1).max(100).default(50).describe('Max spaces to return (1-100, default 50)'),
    },
  • The ReunionClient class with getRecords method used by the handler to fetch coworking space data from the OpenDataSoft API at data.regionreunion.com.
    export class ReunionClient {
      private readonly baseUrl = 'https://data.regionreunion.com/api/explore/v2.1/';
      private readonly timeout = 30000;
      private readonly maxRetries = 2;
      private readonly metadataCache = new Map<string, Promise<DatasetMetadata | undefined>>();
      private readonly recordsCache = new Map<string, { value: unknown; expiresAt: number }>();
    
      /**
       * Fetch records from a dataset
       */
      async getRecords<T extends RecordObject = RecordObject>(
        datasetId: string,
        params: ODSQueryParams = {}
      ): Promise<ODSResponse<T>> {
        const url = this.buildUrl(`/catalog/datasets/${datasetId}/records`, params);
    
        if (REFERENTIAL_DATASETS.has(datasetId)) {
          const now = Date.now();
          const cached = this.recordsCache.get(url);
          if (cached && cached.expiresAt > now) {
            return cached.value as ODSResponse<T>;
          }
          const value = await this.fetchJson<ODSResponse<T>>(url);
          this.recordsCache.set(url, { value, expiresAt: now + REFERENTIAL_TTL_MS });
          return value;
        }
    
        return this.fetchJson<ODSResponse<T>>(url);
      }
Behavior3/5

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

Without annotations, the description partially compensates by noting it's a list with coarse-location filter and describes return fields. However, it lacks details on safety (read-only), rate limits, or pagination.

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

Conciseness5/5

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

Two sentences front-loaded with purpose, each sentence adds value. No unnecessary words.

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?

With no output schema, description lists all return fields and explains filtering. Sufficient for a simple listing tool. Could mention pagination or default limit behavior more explicitly.

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

Parameters3/5

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

Schema coverage is 100% with each parameter described. The description adds little beyond schema: 'commune' already has prefix match description in schema. Baseline 3 is appropriate.

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 it lists coworking spaces in La Réunion with specific details returned. It differentiates from sibling list tools by focusing on coworking spaces only.

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

Usage Guidelines4/5

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

Explicitly mentions target users (remote workers, freelancers, business travelers) and context. Does not state when not to use, but context implies it's specifically for coworking spaces.

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