Meilisearch MCP Server

Instructions

Implementation Reference

• src/tools/vector-tools.ts:25-37 (handler)

  Handler function that enables the vector search experimental feature by posting to the Meilisearch /experimental-features endpoint with vectorStore: true, and returns the response or error.

    async () => {
      try {
        const response = await apiClient.post('/experimental-features', {
          vectorStore: true,
        });
        return {
          content: [{ type: "text", text: JSON.stringify(response.data, null, 2) }],
        };
      } catch (error) {
        return createErrorResponse(error);
      }
    }
  );

• src/tools/vector-tools.ts:21-37 (registration)

  Registers the enable-vector-search tool on the MCP server with no input schema and the inline handler function.

  server.tool(
    "enable-vector-search",
    "Enable the vector search experimental feature in Meilisearch",
    {},
    async () => {
      try {
        const response = await apiClient.post('/experimental-features', {
          vectorStore: true,
        });
        return {
          content: [{ type: "text", text: JSON.stringify(response.data, null, 2) }],
        };
      } catch (error) {
        return createErrorResponse(error);
      }
    }
  );

• src/index.ts:68-68 (registration)

  Registers all vector tools, including enable-vector-search, by calling registerVectorTools on the main MCP server instance.

  registerVectorTools(server);