Skip to main content
Glama

update-customer

Modify customer details in Shopify, including contact information, tags, notes, tax status, and custom fields, using the customer ID.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesShopify customer ID, numeric excluding gid prefix
firstNameNo
lastNameNo
emailNo
phoneNo
tagsNo
noteNo
taxExemptNo
metafieldsNo

Implementation Reference

  • The main execute function that implements the update-customer tool logic. It constructs a GraphQL mutation to update customer data, handles the conversion of numeric ID to GID format, validates input, handles errors, and returns the updated customer information with properly formatted metafields.
    execute: async (input: UpdateCustomerInput) => {
      try {
        const { id, acceptsMarketing, ...customerFields } = input;
    
        // Convert numeric ID to GID format
        const customerGid = `gid://shopify/Customer/${id}`;
    
        // Log a warning if acceptsMarketing was provided
        if (acceptsMarketing !== undefined) {
          console.warn(
            "The acceptsMarketing field is not supported by the Shopify API and will be ignored"
          );
        }
    
        const query = gql`
          mutation customerUpdate($input: CustomerInput!) {
            customerUpdate(input: $input) {
              customer {
                id
                firstName
                lastName
                email
                phone
                tags
                note
                taxExempt
                metafields(first: 10) {
                  edges {
                    node {
                      id
                      namespace
                      key
                      value
                    }
                  }
                }
              }
              userErrors {
                field
                message
              }
            }
          }
        `;
    
        const variables = {
          input: {
            id: customerGid,
            ...customerFields
          }
        };
    
        const data = (await shopifyClient.request(query, variables)) as {
          customerUpdate: {
            customer: any;
            userErrors: Array<{
              field: string;
              message: string;
            }>;
          };
        };
    
        // If there are user errors, throw an error
        if (data.customerUpdate.userErrors.length > 0) {
          throw new Error(
            `Failed to update customer: ${data.customerUpdate.userErrors
              .map((e) => `${e.field}: ${e.message}`)
              .join(", ")}`
          );
        }
    
        // Format and return the updated customer
        const customer = data.customerUpdate.customer;
    
        // Format metafields if they exist
        const metafields =
          customer.metafields?.edges.map((edge: any) => edge.node) || [];
    
        return {
          customer: {
            id: customer.id,
            firstName: customer.firstName,
            lastName: customer.lastName,
            email: customer.email,
            phone: customer.phone,
            tags: customer.tags,
            note: customer.note,
            taxExempt: customer.taxExempt,
            metafields
          }
        };
      } catch (error) {
        console.error("Error updating customer:", error);
        throw new Error(
          `Failed to update customer: ${
            error instanceof Error ? error.message : String(error)
          }`
        );
      }
    }
  • Zod schema definition for update-customer input validation. Defines all optional fields including firstName, lastName, email, phone, tags, note, acceptsMarketing (deprecated), taxExempt, and metafields with proper type constraints.
    const UpdateCustomerInputSchema = z.object({
      id: z.string().regex(/^\d+$/, "Customer ID must be numeric"),
      firstName: z.string().optional(),
      lastName: z.string().optional(),
      email: z.string().email().optional(),
      phone: z.string().optional(),
      tags: z.array(z.string()).optional(),
      note: z.string().optional(),
      // acceptsMarketing field is deprecated as it's not supported in the API
      acceptsMarketing: z.boolean().optional(),
      taxExempt: z.boolean().optional(),
      metafields: z
        .array(
          z.object({
            id: z.string().optional(),
            namespace: z.string().optional(),
            key: z.string().optional(),
            value: z.string(),
            type: z.string().optional()
          })
        )
        .optional()
    });
  • src/index.ts:219-252 (registration)
    MCP server registration of the update-customer tool. Registers the tool with its input schema and creates a handler that calls updateCustomer.execute() and returns the result as JSON text content.
    // Add the updateCustomer tool
    server.tool(
      "update-customer",
      {
        id: z
          .string()
          .regex(/^\d+$/, "Customer ID must be numeric")
          .describe("Shopify customer ID, numeric excluding gid prefix"),
        firstName: z.string().optional(),
        lastName: z.string().optional(),
        email: z.string().email().optional(),
        phone: z.string().optional(),
        tags: z.array(z.string()).optional(),
        note: z.string().optional(),
        taxExempt: z.boolean().optional(),
        metafields: z
          .array(
            z.object({
              id: z.string().optional(),
              namespace: z.string().optional(),
              key: z.string().optional(),
              value: z.string(),
              type: z.string().optional()
            })
          )
          .optional()
      },
      async (args) => {
        const result = await updateCustomer.execute(args);
        return {
          content: [{ type: "text", text: JSON.stringify(result) }]
        };
      }
    );
  • Complete tool object definition including name, description, schema reference, initialize method for GraphQL client setup, and the execute handler containing all business logic.
    const updateCustomer = {
      name: "update-customer",
      description: "Update a customer's information",
      schema: UpdateCustomerInputSchema,
    
      // Add initialize method to set up the GraphQL client
      initialize(client: GraphQLClient) {
        shopifyClient = client;
      },
    
      execute: async (input: UpdateCustomerInput) => {
        try {
          const { id, acceptsMarketing, ...customerFields } = input;
    
          // Convert numeric ID to GID format
          const customerGid = `gid://shopify/Customer/${id}`;
    
          // Log a warning if acceptsMarketing was provided
          if (acceptsMarketing !== undefined) {
            console.warn(
              "The acceptsMarketing field is not supported by the Shopify API and will be ignored"
            );
          }
    
          const query = gql`
            mutation customerUpdate($input: CustomerInput!) {
              customerUpdate(input: $input) {
                customer {
                  id
                  firstName
                  lastName
                  email
                  phone
                  tags
                  note
                  taxExempt
                  metafields(first: 10) {
                    edges {
                      node {
                        id
                        namespace
                        key
                        value
                      }
                    }
                  }
                }
                userErrors {
                  field
                  message
                }
              }
            }
          `;
    
          const variables = {
            input: {
              id: customerGid,
              ...customerFields
            }
          };
    
          const data = (await shopifyClient.request(query, variables)) as {
            customerUpdate: {
              customer: any;
              userErrors: Array<{
                field: string;
                message: string;
              }>;
            };
          };
    
          // If there are user errors, throw an error
          if (data.customerUpdate.userErrors.length > 0) {
            throw new Error(
              `Failed to update customer: ${data.customerUpdate.userErrors
                .map((e) => `${e.field}: ${e.message}`)
                .join(", ")}`
            );
          }
    
          // Format and return the updated customer
          const customer = data.customerUpdate.customer;
    
          // Format metafields if they exist
          const metafields =
            customer.metafields?.edges.map((edge: any) => edge.node) || [];
    
          return {
            customer: {
              id: customer.id,
              firstName: customer.firstName,
              lastName: customer.lastName,
              email: customer.email,
              phone: customer.phone,
              tags: customer.tags,
              note: customer.note,
              taxExempt: customer.taxExempt,
              metafields
            }
          };
        } catch (error) {
          console.error("Error updating customer:", error);
          throw new Error(
            `Failed to update customer: ${
              error instanceof Error ? error.message : String(error)
            }`
          );
        }
      }
    };
  • src/index.ts:70-70 (registration)
    Initialization of the updateCustomer tool with the Shopify GraphQL client, which is required before the tool can execute mutations.
    updateCustomer.initialize(shopifyClient);
Behavior1/5

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

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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/anass319/shopify-MCP'

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