Skip to main content
Glama
devlimelabs

Meilisearch MCP Server

by devlimelabs

search

Find documents in a Meilisearch index using queries, filters, and sorting to retrieve relevant results.

Instructions

Search for documents in a Meilisearch index

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
indexUidYesUnique identifier of the index
qYesSearch query
limitNoMaximum number of results to return (default: 20)
offsetNoNumber of results to skip (default: 0)
filterNoFilter query to apply
sortNoAttributes to sort by, e.g. ["price:asc"]
facetsNoFacets to return
attributesToRetrieveNoAttributes to include in results
attributesToCropNoAttributes to crop
cropLengthNoLength at which to crop cropped attributes
attributesToHighlightNoAttributes to highlight
highlightPreTagNoTag to insert before highlighted text
highlightPostTagNoTag to insert after highlighted text
showMatchesPositionNoWhether to include match positions in results
matchingStrategyNoMatching strategy: 'all' or 'last'

Implementation Reference

  • The core handler function for the 'search' tool. It takes search parameters and makes a POST request to the Meilisearch /indexes/{indexUid}/search endpoint, returning the JSON response or an error.
    async ({ indexUid, q, limit, offset, filter, sort, facets, attributesToRetrieve, attributesToCrop, cropLength, attributesToHighlight, highlightPreTag, highlightPostTag, showMatchesPosition, matchingStrategy }: SearchParams) => { try { const response = await apiClient.post(`/indexes/${indexUid}/search`, { q, limit, offset, filter, sort, facets, attributesToRetrieve, attributesToCrop, cropLength, attributesToHighlight, highlightPreTag, highlightPostTag, showMatchesPosition, matchingStrategy, }); return { content: [{ type: 'text', text: JSON.stringify(response.data, null, 2) }], }; } catch (error) { return createErrorResponse(error); } }
  • Zod schema defining the input parameters for the 'search' tool.
    indexUid: z.string().describe('Unique identifier of the index'), q: z.string().describe('Search query'), limit: z.number().min(1).max(1000).optional().describe('Maximum number of results to return (default: 20)'), offset: z.number().min(0).optional().describe('Number of results to skip (default: 0)'), filter: z.string().optional().describe('Filter query to apply'), sort: z.array(z.string()).optional().describe('Attributes to sort by, e.g. ["price:asc"]'), facets: z.array(z.string()).optional().describe('Facets to return'), attributesToRetrieve: z.array(z.string()).optional().describe('Attributes to include in results'), attributesToCrop: z.array(z.string()).optional().describe('Attributes to crop'), cropLength: z.number().optional().describe('Length at which to crop cropped attributes'), attributesToHighlight: z.array(z.string()).optional().describe('Attributes to highlight'), highlightPreTag: z.string().optional().describe('Tag to insert before highlighted text'), highlightPostTag: z.string().optional().describe('Tag to insert after highlighted text'), showMatchesPosition: z.boolean().optional().describe('Whether to include match positions in results'), matchingStrategy: z.string().optional().describe("Matching strategy: 'all' or 'last'"), },
  • Direct registration of the 'search' tool on the MCP server instance within the registerSearchTools function.
    server.tool( 'search', 'Search for documents in a Meilisearch index', { indexUid: z.string().describe('Unique identifier of the index'), q: z.string().describe('Search query'), limit: z.number().min(1).max(1000).optional().describe('Maximum number of results to return (default: 20)'), offset: z.number().min(0).optional().describe('Number of results to skip (default: 0)'), filter: z.string().optional().describe('Filter query to apply'), sort: z.array(z.string()).optional().describe('Attributes to sort by, e.g. ["price:asc"]'), facets: z.array(z.string()).optional().describe('Facets to return'), attributesToRetrieve: z.array(z.string()).optional().describe('Attributes to include in results'), attributesToCrop: z.array(z.string()).optional().describe('Attributes to crop'), cropLength: z.number().optional().describe('Length at which to crop cropped attributes'), attributesToHighlight: z.array(z.string()).optional().describe('Attributes to highlight'), highlightPreTag: z.string().optional().describe('Tag to insert before highlighted text'), highlightPostTag: z.string().optional().describe('Tag to insert after highlighted text'), showMatchesPosition: z.boolean().optional().describe('Whether to include match positions in results'), matchingStrategy: z.string().optional().describe("Matching strategy: 'all' or 'last'"), }, async ({ indexUid, q, limit, offset, filter, sort, facets, attributesToRetrieve, attributesToCrop, cropLength, attributesToHighlight, highlightPreTag, highlightPostTag, showMatchesPosition, matchingStrategy }: SearchParams) => { try { const response = await apiClient.post(`/indexes/${indexUid}/search`, { q, limit, offset, filter, sort, facets, attributesToRetrieve, attributesToCrop, cropLength, attributesToHighlight, highlightPreTag, highlightPostTag, showMatchesPosition, matchingStrategy, }); return { content: [{ type: 'text', text: JSON.stringify(response.data, null, 2) }], }; } catch (error) { return createErrorResponse(error); } } );
  • src/index.ts:66-66 (registration)
    Top-level call to registerSearchTools, which registers the 'search' tool among others, in the main server initialization.
    registerSearchTools(server);

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/devlimelabs/meilisearch-ts-mcp'

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