Connect BigCommerce to Claude: Automate Support & Order Fulfillment

If you want Claude to instantly pull BigCommerce order statuses, manage product catalogs, or audit customer data, you need to connect the two platforms directly. Native plugins do not offer the depth required for complex e-commerce automation. The engineering standard is building a Model Context Protocol (MCP) server that translates Claude's tool calls into BigCommerce REST API requests. I will show you exactly how to generate a managed MCP server for BigCommerce using Truto and connect it to Claude in minutes. If your team uses ChatGPT, check out our guide on connecting BigCommerce to ChatGPT or read our broader architectural overview on connecting BigCommerce to AI Agents.

Giving a Large Language Model (LLM) read and write access to an e-commerce backend is a serious engineering challenge. You either spend weeks building, hosting, and maintaining a custom MCP server, or you use a managed infrastructure layer that handles the boilerplate dynamically. This guide breaks down exactly how to use Truto to generate a secure MCP server for BigCommerce, connect it natively to Claude Desktop or your custom Claude agent, and execute complex workflows using natural language.

The Engineering Reality of the BigCommerce API

A custom MCP server is essentially a self-hosted integration layer. While the Model Context Protocol provides a predictable way for models to discover tools, implementing it against vendor APIs requires heavy lifting. The BigCommerce REST API has specific architectural quirks that make building a reliable agent integration difficult.

1. The V2 vs. V3 API Fragmentation BigCommerce operates across two major API versions simultaneously. The Orders API is heavily rooted in V2, which relies on traditional page-based pagination (page and limit). Meanwhile, the Catalog API (Products, Variants, Categories) lives in V3, which utilizes cursor-based pagination. If you hand Claude the raw OpenAPI specification, it will struggle to understand which pagination strategy to use for which endpoint. Truto abstracts this entirely. When generating the MCP tool schema, Truto normalizes the pagination inputs, explicitly instructing Claude on how to handle cursors and limits regardless of the underlying BigCommerce API version.

2. Deeply Nested Catalog Structures Updating a product in BigCommerce is rarely a flat operation. Products have variants, modifiers, custom fields, and complex pricing rules. Similar to the complex schemas we discussed in our guide to connecting Attio to Claude, a naive MCP implementation will often result in Claude hallucinating payload structures or failing validation checks. Truto solves this by deriving MCP tool definitions directly from curated documentation records. The generated JSON Schema for the body_schema strictly enforces required fields and nested object structures, ensuring Claude formats its requests exactly as BigCommerce expects.

3. Strict Rate Limit Enforcement BigCommerce enforces strict concurrency and rate limits. A highly active AI agent can easily burn through these limits when executing parallel tool calls. Truto does not silently absorb or infinitely retry these errors. Instead, Truto normalizes the upstream rate limit information into standardized IETF headers (ratelimit-limit, ratelimit-remaining, ratelimit-reset). When BigCommerce returns an HTTP 429, Truto passes that error directly back to Claude. This is intentional: it forces the agentic framework to understand the backoff requirement and handle its own retry logic intelligently.

How to Generate a BigCommerce MCP Server

Truto dynamically generates MCP servers for any connected integrated account. You do not need to write integration-specific code. You can generate the server via the Truto UI or programmatically via the API.

Method 1: Via the Truto UI

For internal tooling and rapid prototyping, the UI is the fastest path.

1. Navigate to the Integrated Accounts page in your Truto dashboard.
2. Select your connected BigCommerce account.
3. Click the MCP Servers tab.
4. Click Create MCP Server.
5. Select your desired configuration (e.g., read-only access, specific tags, or expiration dates).
6. Copy the generated MCP server URL (it will look like https://api.truto.one/mcp/a1b2c3d4...).

Method 2: Via the Truto API

If you are building a multi-tenant SaaS application and need to provision MCP servers for your customers dynamically, use the REST API.

// POST /integrated-account/:id/mcp
 
const response = await fetch('https://api.truto.one/integrated-account/YOUR_ACCOUNT_ID/mcp', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_TRUTO_API_TOKEN',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    name: "Claude BigCommerce Server",
    config: {
      methods: ["read", "write"] // Optional: restrict to specific operations
    }
  })
});
 
const data = await response.json();
console.log(data.url); // The MCP server URL to pass to Claude

This endpoint validates that the BigCommerce integration has tools available, generates a secure token, hashes it for secure storage, and returns the ready-to-use URL.

How to Connect the MCP Server to Claude

Once you have your Truto MCP URL, connecting it to Claude takes seconds. You can do this through the Claude Desktop UI or by editing the configuration file directly.

Method A: Via the Claude UI

1. Open Claude Desktop or the Claude Web interface.
2. Navigate to Settings -> Integrations (or Connectors depending on your plan tier).
3. Click Add MCP Server or Add custom connector.
4. Paste the Truto MCP URL you generated.
5. Click Add.

Claude will immediately perform a JSON-RPC 2.0 handshake (initialize), request the available capabilities (tools/list), and load the BigCommerce tools into its context window.

Method B: Via Manual Config File

If you are running Claude Desktop locally and prefer managing configurations via code, you can edit the claude_desktop_config.json file. Truto provides an SSE (Server-Sent Events) adapter for MCP.

Open your config file (typically located at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows) and add the following:

{
  "mcpServers": {
    "bigcommerce": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-sse",
        "https://api.truto.one/mcp/YOUR_TRUTO_MCP_TOKEN"
      ]
    }
  }
}

Restart Claude Desktop. The tools will now be available in your chats.

graph TD
  A[Claude Desktop] -->|JSON-RPC 2.0| B(Truto MCP Server<br>Endpoint)
  B -->|Token Validation| C[Secure Token Storage]
  B -->|Proxy API| D[BigCommerce REST API]
  D -->|Raw JSON| B
  B -->|Normalized Tool Response| A

BigCommerce Tool Inventory for Claude

Truto automatically translates BigCommerce API endpoints into descriptive, snake_case tool names with strict JSON schemas. Here are the most critical tools available to Claude.

list_all_bigcommerce_orders

• Description: Gets a list of orders using the filter query. The default sort is by order id, from lowest to highest. Supports filtering by status, customer ID, and date ranges.
• Example Prompt: "Pull a list of all BigCommerce orders placed today that are currently marked as 'Awaiting Fulfillment'."

get_single_bigcommerce_order_by_id

• Description: Get a single Order by its ID. Returns the complete order object including shipping addresses, billing details, and total amounts.
• Example Prompt: "Check the status of order ID 10452 and tell me the shipping address and total order value."

list_all_bigcommerce_products

• Description: Returns a list of Products. You can filter by their names, price, brands, inventory levels, and visibility status.
• Example Prompt: "Find all products in the catalog priced under $50 that currently have zero inventory."

list_all_bigcommerce_customers

• Description: Returns a list of Customers. They can be filtered by their names, emails, phones, or company names.
• Example Prompt: "Search our BigCommerce customers for anyone with the email domain @acmecorp.com."

get_single_bigcommerce_customer_by_id

• Description: Get a single Customer by their ID. Returns profile data, store credit, and customer group assignments.
• Example Prompt: "Look up customer ID 8891 and tell me if they belong to the 'Wholesale' customer group."

Here is the complete inventory of additional BigCommerce tools available. For full schema details, visit the BigCommerce integration page.

• get_single_bigcommerce_product_by_id: Get a single product by its ID.

Workflows in Action

Once connected, Claude can orchestrate complex workflows by chaining these tools together. Here is how real-world automation looks in practice.

Scenario 1: Automated Order Auditing & Fulfillment Check

Customer support teams waste hours cross-referencing order statuses and customer histories. As we highlighted in our ChatGPT order tracking guide, you can hand this entirely to Claude.

User Prompt: "Check order 10452. Tell me its current status, what the customer bought, and whether this customer has placed any other orders with us in the past."

Execution Steps:

1. Claude calls get_single_bigcommerce_order_by_id with id: 10452.
2. Claude parses the response, extracting the status ("Awaiting Fulfillment") and the customer_id (e.g., 8891).
3. Claude calls list_all_bigcommerce_orders using the query parameter customer_id: 8891 to fetch historical orders.
4. Claude synthesizes the data and replies: "Order 10452 is currently Awaiting Fulfillment. The customer purchased a Mechanical Keyboard. This is a returning customer who has placed 3 previous orders, all of which were successfully delivered."

Scenario 2: Catalog Auditing & Inventory Management

E-commerce managers need to identify catalog anomalies quickly without writing custom reports or exporting CSVs.

User Prompt: "Pull all active products that have an inventory level of zero. Group them by brand and give me a summary."

Execution Steps:

1. Claude calls list_all_bigcommerce_products with query parameters is_visible: true and inventory_level: 0.
2. If the result set is large, Claude receives a next_cursor in the response and automatically calls the tool again to fetch the next page.
3. Claude analyzes the aggregated JSON response, groups the items by the brand_id field, and outputs a clean markdown table summarizing the out-of-stock items.

Security and Access Control

Exposing a production BigCommerce store to an AI agent requires strict boundaries. Truto's MCP architecture provides several layers of security to ensure Claude only does exactly what you permit.

• Method Filtering: You can restrict the MCP server to read-only operations. By setting config.methods: ["read"] during creation, Truto will only generate tools for get and list operations. Claude will physically not have the tools to create or delete records.
• Tag Filtering: If you only want Claude to access the catalog and not customer data, you can use config.tags: ["catalog"]. Only endpoints tagged with "catalog" will be exposed to the LLM.
• Token Authentication: By default, the MCP URL is a secure, hashed token. For enterprise environments, you can enforce require_api_token_auth: true. This forces the MCP client to provide a valid Truto API token in the Authorization header, adding a second layer of identity verification.
• Ephemeral Access: You can provision temporary MCP servers by setting an expires_at datetime. Truto uses automated TTLs and scheduled background tasks to automatically destroy the token and revoke access at the exact millisecond it expires. This is perfect for granting temporary access to contractors or short-lived agentic tasks.

Strategic Wrap-Up

Building a custom MCP server for BigCommerce is a distraction from your core product. You have to handle OAuth flows, V2/V3 pagination normalization, rate limit backoffs, and JSON schema generation. Truto's managed MCP servers eliminate this boilerplate entirely, just as they do when connecting Anthropic to Claude for administrative tasks.

By routing Claude's tool calls through Truto, you get instant, secure, and documented access to the entire BigCommerce API surface area. You configure the guardrails, and Truto handles the execution pipeline.