Skip to main content
Glama
OrionPotter

Meilisearch MCP Server

by OrionPotter

search

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

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 asynchronous handler function for the 'search' MCP tool. It takes search parameters, makes a POST request to the Meilisearch `/indexes/${indexUid}/search` endpoint using apiClient, returns the JSON response or an error response.
    async ({ 
      indexUid, 
      q, 
      limit, 
      offset, 
      filter, 
      sort, 
      facets, 
      attributesToRetrieve, 
      attributesToCrop, 
      cropLength, 
      attributesToHighlight, 
      highlightPreTag, 
      highlightPostTag, 
      showMatchesPosition, 
      matchingStrategy 
    }: SearchParams) => {
      try {
        const response = await apiClient.post(`/indexes/${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 input schema defining parameters for the 'search' tool, including indexUid, q (query), limit, offset, filter, sort, facets, cropping options, highlighting options, etc.
      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'"),
    },
  • MCP server.tool() registration for the 'search' tool, specifying name 'search', description, input schema, and handler 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);
        }
      }
    );
  • TypeScript interface SearchParams defining the types for search parameters used in the handler.
    interface SearchParams {
      indexUid: string;
      q: string;
      limit?: number;
      offset?: number;
      filter?: string;
      sort?: string[];
      facets?: string[];
      attributesToRetrieve?: string[];
      attributesToCrop?: string[];
      cropLength?: number;
      attributesToHighlight?: string[];
      highlightPreTag?: string;
      highlightPostTag?: string;
      showMatchesPosition?: boolean;
      matchingStrategy?: string;
    }
  • src/index.ts:66-66 (registration)
    Call to registerSearchTools(server) in the main server initialization, which registers the 'search' tool among other search tools.
    registerSearchTools(server);
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the basic action but doesn't describe what the search returns (e.g., result format, pagination behavior, error conditions), whether it's read-only (implied but not explicit), or any performance characteristics. For a search tool with 15 parameters and no annotations, this is a significant gap.

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?

The description is a single, efficient sentence that states the core purpose without any fluff. It's appropriately sized and front-loaded, with every word earning its place. No structural issues or unnecessary elaboration.

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

Completeness2/5

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

Given the complexity (15 parameters, no output schema, no annotations), the description is incomplete. It doesn't explain what the search returns, how results are structured, or any behavioral aspects like error handling or performance. For a search tool with rich parameter options, this minimal description leaves too many questions unanswered for effective agent use.

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 description coverage is 100%, meaning all parameters are documented in the schema itself. The description doesn't add any parameter-specific information beyond what's in the schema (e.g., it doesn't explain how parameters interact or provide usage examples). With high schema coverage, the baseline is 3 even without additional param details in the description.

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

Purpose4/5

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

The description clearly states the action ('Search for documents') and target resource ('in a Meilisearch index'), providing a specific verb+resource combination. However, it doesn't differentiate from sibling tools like 'facet-search', 'multi-search', or 'vector-search', which are also search-related operations, so it misses full sibling distinction.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. There are multiple search-related sibling tools (e.g., 'facet-search', 'multi-search', 'vector-search'), but the description doesn't mention any of them or explain when this basic search is appropriate versus more specialized searches.

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/OrionPotter/iflow-mcp_meilisearch-ts-mcp'

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