www/apps/book/app/learn/introduction/build-with-llms-ai/mcp-server/page.mdx
import { Tabs, TabsContent, TabsContentWrapper, TabsList, TabsTrigger, ChildDocs, Link, Prerequisites, CodeTab, CodeTabs } from "docs-ui"
export const metadata = {
title: ${pageNumber} Medusa MCP Remote Server,
}
The Medusa documentation provides a remote Model Context Protocol (MCP) server that allows you to find information from the Medusa documentation right in your IDEs or AI tools, such as Cursor.
Medusa hosts a Streamable HTTP MCP server at https://docs.medusajs.com/mcp that you can add to AI agents supporting MCP server connections.
This MCP server is available for Cloud users only. It requires authenticating with your Cloud account to use it.
The MCP server supports two authentication methods:
<Prerequisites items={[ { text: "Cloud account", link: "!cloud!" } ]} />
To connect to the Medusa MCP server in Claude Code, run the following command in your terminal:
<CodeTabs group="mcp-server-auth"> <CodeTab label="OAuth" value="oauth">claude mcp add --transport http medusa https://docs.medusajs.com/mcp
claude mcp add --transport http medusa https://docs.medusajs.com/mcp --header "Authorization: Bearer {token}"
Then, start Claude Code and authenticate with your Cloud account:
claude
/mcp # for oauth
If you're connecting with OAuth, select the medusa MCP server and choose "Authenticate". This will open a browser window where you can log into your Cloud account to authenticate.
To connect to the Medusa MCP server in Codex, use one of the following methods:
<CodeTabs group="mcp-server-auth"> <CodeTab label="OAuth" value="oauth">Run the following command in your terminal:
codex mcp add medusa --url https://docs.medusajs.com/mcp
[mcp_servers.medusa]
url = "https://docs.medusajs.com/mcp"
bearer_token_env_var = "{token}"
If you're connecting with OAuth, run the following command in your terminal to authenticate with your Cloud account:
codex mcp login medusa
This will open a browser window where you can log into your Cloud account to authenticate.
Add the following to your .cursor/mcp.json file or Cursor settings, as explained in the Cursor documentation:
{
"mcpServers": {
"medusa": {
"url": "https://docs.medusajs.com/mcp"
}
}
}
{
"mcpServers": {
"medusa": {
"url": "https://docs.medusajs.com/mcp",
"headers": {
"Authorization": "Bearer {token}"
}
}
}
}
If you're connecting with OAuth, open Settings -> Tools & MCPs and click "Connect" next to the medusa MCP server. This will open a browser window where you can log into your Cloud account to authenticate.
To manually connect to the Medusa MCP server in VSCode, add the following to your .vscode/mcp.json file in your workspace:
{
"servers": {
"medusa": {
"type": "http",
"url": "https://docs.medusajs.com/mcp"
}
}
}
{
"servers": {
"medusa": {
"type": "http",
"url": "https://docs.medusajs.com/mcp",
"headers": {
"Authorization": "Bearer {token}"
}
}
}
}
If you're connecting with OAuth, once you start the MCP server connection, you will be prompted to authenticate with your Cloud account in a browser window. Log in to authenticate and start using the Medusa MCP server in VSCode.
Add the following to your OpenCode config file (for example, ~/.config/opencode/opencode.json):
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"medusa": {
"type": "remote",
"url": "https://docs.medusajs.com/mcp"
}
},
}
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"medusa": {
"type": "remote",
"url": "https://docs.medusajs.com/mcp",
"headers": {
"Authorization": "Bearer {token}"
},
"oauth": false
}
},
}
If you're connecting with OAuth, run the following command in your terminal to authenticate with your Cloud account:
opencode mcp auth medusa
This will open a browser window where you can log into your Cloud account to authenticate.
After connecting to the Medusa MCP server in your AI tool or IDE, you can start asking questions or requesting your AI assistant to build Medusa customizations. It will fetch the relevant information from the Medusa documentation and provide you with accurate answers, code snippets, and explanations.
For example, you can ask:
Beyond answering questions from the documentation, the MCP server provides tools that return curated, step-by-step implementation guides for common tasks. These guides tell your AI agent exactly which Medusa APIs and patterns to use, so it doesn't have to infer them.
The following chapters cover each tool, who it's useful for, and how to use it:
<ChildDocs type="item" onlyTopLevel />