Install AI Tools

B2C Commerce tools, documentation, and skills for your assistant.

Claude

Using Claude Desktop? See Claude Desktop (Cowork) setup.

Install the plugin Recommended

bash

claude plugin marketplace add SalesforceCommerceCloud/b2c-developer-tooling
claude plugin install b2c-dx-mcp@b2c-developer-tooling

Start a new Claude Code session. To install for the current project only, run it from your project directory with --scope project.

Manual MCP setup

bash

claude mcp add --transport stdio --scope user b2c-dx-mcp -- npx -y @salesforce/b2c-dx-mcp@latest

Start a new session. To configure the current project only, run it from your project directory with --scope project. See Claude Code MCP setup.

Codex/ChatGPT

Using the ChatGPT desktop app (ChatGPT Work)? See ChatGPT Work setup.

Install the plugin Recommended

bash

codex plugin marketplace add SalesforceCommerceCloud/b2c-developer-tooling
codex plugin add b2c-dx-mcp@b2c-developer-tooling

Start a new Codex session in your project. Codex plugins also work in ChatGPT Work.

Manual MCP setup

bash

codex mcp add b2c-dx-mcp -- npx -y @salesforce/b2c-dx-mcp@latest

Or add this to ~/.codex/config.toml (or $CODEX_HOME/config.toml if customized):

toml

[mcp_servers.b2c-dx-mcp]
command = "npx"
args = ["-y", "@salesforce/b2c-dx-mcp@latest"]

Start a new session. See Codex MCP configuration.

VS Code

Install in VS Code

Install the plugin Recommended

Open the Command Palette (Cmd/Ctrl+Shift+P) and run Chat: Install Plugin from Source.
Enter SalesforceCommerceCloud/b2c-developer-tooling.
Select b2c-dx-mcp and follow the installation prompts.
Start a new chat in GitHub Copilot.

Manual MCP setup

Add this to .vscode/mcp.json in your workspace:

json

{
  "servers": {
    "b2c-dx-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@salesforce/b2c-dx-mcp@latest"]
    }
  }
}

See VS Code MCP setup.

Copilot CLI setup

Cursor

Install in Cursor

Reload the MCP server in Cursor after installation.

Manual MCP setup

Add this to .cursor/mcp.json in your project:

json

{
  "mcpServers": {
    "b2c-dx-mcp": {
      "command": "npx",
      "args": ["-y", "@salesforce/b2c-dx-mcp@latest"]
    }
  }
}

For all projects, use ~/.cursor/mcp.json instead.

See Cursor's MCP documentation.

OpenCode

Add this to opencode.json in your project:

json

{
  "mcp": {
    "b2c-dx-mcp": {
      "type": "local",
      "command": ["npx", "-y", "@salesforce/b2c-dx-mcp@latest"],
      "enabled": true
    }
  }
}

Restart OpenCode. For all projects, use ~/.config/opencode/opencode.json. See OpenCode MCP setup.

Gemini

Run:

bash

gemini mcp add --scope user b2c-dx-mcp -- npx -y @salesforce/b2c-dx-mcp@latest

Start a new Gemini CLI session. To configure the current project only, run it from your project directory with --scope project. See Gemini CLI MCP setup.

No separate skills plugins needed.

Other clients and manual setup →

View as Markdown

@salesforce/b2c-tooling-sdk / operations/mrt / runMrtWithFallback

Function: runMrtWithFallback()

runMrtWithFallback<T>(options, branches): Promise<MrtBackendRun<T>>

Defined in: packages/b2c-tooling-sdk/src/operations/mrt/mrt-backend.ts:168

Resolves the backend and runs the matching branch.

legacy (explicit or auto with no SCAPI config): runs the legacy branch.
scapi (explicit): runs the SCAPI branch with no fallback — every error surfaces, including 409 Conflict.
auto with a SCAPI connection: runs SCAPI optimistically; on a safe rejection (a definite pre-execution client error or invalid_scope) it warns and retries on legacy — but only when a legacy target exists (RunMrtWithFallbackOptions.canFallbackToLegacy). With no legacy credentials, the original SCAPI error is rethrown so the user sees the real failure rather than a "provide an API key" message. Ambiguous failures (429, 5xx, network) and 409 Conflict never fall back — a mutating deploy must not cross backends after the request may have reached SCAPI.

Type Parameters

T

T

Parameters

options

RunMrtWithFallbackOptions

branches

MrtBackendBranches<T>

Returns

Promise<MrtBackendRun<T>>

the backend that served the call and its result.