Skip to main content
Glama

get_collection

Retrieve a single Shopify collection by GID, returning its title, handle, sort order, description, and the first N products. Set productsFirst to 0 for metadata-only. Indicates if more products exist.

Instructions

Fetch a single collection by GID with full details — title, handle, sort order, description, and the first N products inside it. Pass productsFirst=0 for metadata-only when you don't need the products array. Returns a friendly text view; pageInfo flags when more products exist beyond the requested page.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesCollection GID, e.g. 'gid://shopify/Collection/123456'. Get one from list_collections.
productsFirstNoHow many products to include alongside the collection. Pass 0 to skip products entirely (faster for collection-only metadata).

Implementation Reference

  • The main handler function for the 'get_collection' tool. It executes a GraphQL query to fetch a single collection by GID, including its products, and returns a formatted text view.
    server.tool(
      "get_collection",
      "Fetch a single collection by GID with full details — title, handle, sort order, description, and the first N products inside it. Pass productsFirst=0 for metadata-only when you don't need the products array. Returns a friendly text view; pageInfo flags when more products exist beyond the requested page.",
      getCollectionSchema,
      async (args) => {
        const data = await client.graphql<{
          collection:
            | (Collection & {
                products: {
                  edges: Array<{
                    node: {
                      id: string;
                      title: string;
                      handle: string;
                      status: string;
                      featuredImage?: { url: string } | null;
                    };
                  }>;
                  pageInfo: { hasNextPage: boolean };
                };
              })
            | null;
        }>(GET_COLLECTION_QUERY, {
          id: args.id,
          productsFirst: args.productsFirst,
        });
        if (!data.collection) {
          return {
            content: [
              { type: "text" as const, text: `Collection not found: ${args.id}` },
            ],
          };
        }
        const c = data.collection;
        const productLines = c.products.edges.map(
          ({ node }) => `    - ${node.title} [${node.status}] (${node.handle}) — ${node.id}`,
        );
        return {
          content: [
            {
              type: "text" as const,
              text: [
                `${c.title}`,
                `  ID: ${c.id}`,
                `  Handle: ${c.handle}`,
                `  Sort order: ${c.sortOrder ?? "(default)"}`,
                c.description ? `  Description: ${c.description}` : "",
                `  Products (${c.productsCount?.count ?? "?"}):`,
                ...productLines,
                c.products.pageInfo.hasNextPage
                  ? "  (more products available; raise productsFirst to page further)"
                  : "",
              ]
                .filter(Boolean)
                .join("\n"),
            },
          ],
        };
      },
    );
  • Input schema for get_collection: requires 'id' (collection GID string) and optional 'productsFirst' (number, 0-100, default 20).
    const getCollectionSchema = {
      id: z
        .string()
        .describe(
          "Collection GID, e.g. 'gid://shopify/Collection/123456'. Get one from list_collections.",
        ),
      productsFirst: z
        .number()
        .int()
        .min(0)
        .max(100)
        .default(20)
        .describe(
          "How many products to include alongside the collection. Pass 0 to skip products entirely (faster for collection-only metadata).",
        ),
    };
  • Registration of the tool via server.tool() call with name 'get_collection', description, schema, and handler function. This is inside registerCollectionTools().
    server.tool(
      "get_collection",
      "Fetch a single collection by GID with full details — title, handle, sort order, description, and the first N products inside it. Pass productsFirst=0 for metadata-only when you don't need the products array. Returns a friendly text view; pageInfo flags when more products exist beyond the requested page.",
      getCollectionSchema,
      async (args) => {
        const data = await client.graphql<{
          collection:
            | (Collection & {
                products: {
                  edges: Array<{
                    node: {
                      id: string;
                      title: string;
                      handle: string;
                      status: string;
                      featuredImage?: { url: string } | null;
                    };
                  }>;
                  pageInfo: { hasNextPage: boolean };
                };
              })
            | null;
        }>(GET_COLLECTION_QUERY, {
          id: args.id,
          productsFirst: args.productsFirst,
        });
        if (!data.collection) {
          return {
            content: [
              { type: "text" as const, text: `Collection not found: ${args.id}` },
            ],
          };
        }
        const c = data.collection;
        const productLines = c.products.edges.map(
          ({ node }) => `    - ${node.title} [${node.status}] (${node.handle}) — ${node.id}`,
        );
        return {
          content: [
            {
              type: "text" as const,
              text: [
                `${c.title}`,
                `  ID: ${c.id}`,
                `  Handle: ${c.handle}`,
                `  Sort order: ${c.sortOrder ?? "(default)"}`,
                c.description ? `  Description: ${c.description}` : "",
                `  Products (${c.productsCount?.count ?? "?"}):`,
                ...productLines,
                c.products.pageInfo.hasNextPage
                  ? "  (more products available; raise productsFirst to page further)"
                  : "",
              ]
                .filter(Boolean)
                .join("\n"),
            },
          ],
        };
      },
    );
  • The GraphQL query used by the get_collection handler to fetch collection data and its products.
    const GET_COLLECTION_QUERY = /* GraphQL */ `
      query GetCollection($id: ID!, $productsFirst: Int!) {
        collection(id: $id) {
          id
          handle
          title
          description
          sortOrder
          updatedAt
          image { url altText }
          productsCount { count }
          products(first: $productsFirst) {
            edges {
              node {
                id
                title
                handle
                status
                featuredImage { url }
              }
            }
            pageInfo { hasNextPage endCursor }
          }
        }
      }
    `;
  • src/server.ts:63-63 (registration)
    Where registerCollectionTools is called to register all collection tools (including get_collection) on the MCP server.
    registerCollectionTools(s, shopify);
Behavior3/5

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

No annotations are provided, so description carries full burden. Indicates it returns a 'friendly text view' and pageInfo flags, but does not declare read-only nature or potential side effects. Could be more explicit about safety.

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, no waste, key information front-loaded. Efficient and well-structured.

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?

No output schema, but description covers return content (fields, products, pageInfo). Could mention error handling, but sufficient for typical fetch tool.

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

Parameters4/5

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

Schema coverage is 100% (both parameters described). Description adds value by explaining productsFirst use case (0 for metadata-only) and hints at performance, surpassing schema alone.

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?

Description clearly states it fetches a single collection by GID with full details (title, handle, etc.) and products, distinguishing from sibling tools like list_collections (lists), create_collection, delete_collection, update_collection.

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?

Provides guidance on when to use productsFirst=0 for metadata-only, implying use cases. Does not explicitly compare to all sibling tools but offers practical advice for efficient use.

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/miller-joe/shopify-mcp'

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