Skip to main content
Glama
OrionPotter

Meilisearch MCP Server

by OrionPotter

update-documents

Modify existing documents in a Meilisearch index by providing updated JSON data and index identifier to maintain current information.

Instructions

Update documents in a Meilisearch index

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
indexUidYesUnique identifier of the index
documentsYesJSON array of documents to update
primaryKeyNoPrimary key for the documents

Implementation Reference

  • Handler function that executes the tool logic: parses input documents JSON, validates array, prepares params with optional primaryKey, performs PUT request to update documents in Meilisearch via apiClient, returns response or error.
    async ({ indexUid, documents, primaryKey }: UpdateDocumentsParams) => {
      try {
        // Parse the documents string to ensure it's valid JSON
        const parsedDocuments = JSON.parse(documents);
        
        // Ensure documents is an array
        if (!Array.isArray(parsedDocuments)) {
          return {
            isError: true,
            content: [{ type: 'text', text: 'Documents must be a JSON array' }],
          };
        }
        
        const params: Record<string, string> = {};
        if (primaryKey) {
          params.primaryKey = primaryKey;
        }
        
        const response = await apiClient.put(`/indexes/${indexUid}/documents`, parsedDocuments, {
          params,
        });
        return {
          content: [{ type: 'text', text: JSON.stringify(response.data, null, 2) }],
        };
      } catch (error) {
        return createErrorResponse(error);
      }
    }
  • Zod input schema defining parameters for the update-documents tool: indexUid (required string), documents (required JSON string of array), primaryKey (optional string).
    {
      indexUid: z.string().describe('Unique identifier of the index'),
      documents: z.string().describe('JSON array of documents to update'),
      primaryKey: z.string().optional().describe('Primary key for the documents'),
    },
  • MCP server.tool registration for 'update-documents', including description, input schema, and handler function.
    server.tool(
      'update-documents',
      'Update documents in a Meilisearch index',
      {
        indexUid: z.string().describe('Unique identifier of the index'),
        documents: z.string().describe('JSON array of documents to update'),
        primaryKey: z.string().optional().describe('Primary key for the documents'),
      },
      async ({ indexUid, documents, primaryKey }: UpdateDocumentsParams) => {
        try {
          // Parse the documents string to ensure it's valid JSON
          const parsedDocuments = JSON.parse(documents);
          
          // Ensure documents is an array
          if (!Array.isArray(parsedDocuments)) {
            return {
              isError: true,
              content: [{ type: 'text', text: 'Documents must be a JSON array' }],
            };
          }
          
          const params: Record<string, string> = {};
          if (primaryKey) {
            params.primaryKey = primaryKey;
          }
          
          const response = await apiClient.put(`/indexes/${indexUid}/documents`, parsedDocuments, {
            params,
          });
          return {
            content: [{ type: 'text', text: JSON.stringify(response.data, null, 2) }],
          };
        } catch (error) {
          return createErrorResponse(error);
        }
      }
    );
  • src/index.ts:65-65 (registration)
    Top-level call to registerDocumentTools on the MCP server instance, which includes the update-documents tool.
    registerDocumentTools(server);
  • TypeScript interface defining the parameters for the update-documents handler.
    interface UpdateDocumentsParams {
      indexUid: string;
      documents: string;
      primaryKey?: string;
    }

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