Saleor MCP Server
Enables AI assistants to interact with Saleor Commerce instances to fetch data about products, customers, and orders through a read-only GraphQL API integration. Supports secure authentication and domain validation for connecting to Saleor cloud instances.
README
Saleor MCP Server
A Model Context Protocol (MCP) server for Saleor Commerce that provides integration with AI assistants and tools.
Getting Started
The Saleor MCP server allows AI assistants to interact with Saleor instance in order to fetch data about products, customers, and orders. The MCP is read-only - it doesn't trigger any mutations in the Saleor API.
Easiest way to try out the Saleor MCP server is by visiting the production instance deployed at:
https://mcp.saleor.app/
You can connect to the server with Streamable HTTP at https://mcp.saleor.app/mcp endpoint. See the Configuration section below for details on required headers. The production instance is configured to connect to Saleor instances hosted on saleor.cloud domain and it's compatible with Saleor 3.22.
Installation
The following instructions will help you set up the Saleor MCP server locally for development and testing purposes.
Prerequisites
- Python 3.12 or higher
- uv package manager
Setup
-
Clone the repository
git clone git@github.com:saleor/saleor-mcp.git cd saleor-mcp -
Install dependencies
uv sync -
Run the MCP server locally
uv run saleor-mcpThe server will start on
http://localhost:6000
Configuration
X-Saleor-API-URL and X-Saleor-Auth-Token headers
The Saleor MCP server uses two headers to configure connection to the Saleor API:
X-Saleor-API-URL- The URL of the Saleor API endpoint.X-Saleor-Auth-Token- The authentication token for accessing the Saleor API. The token must haveMANAGE_PRODUCTSandMANAGE_ORDERSpermissions to access the available tools.
Make sure to include these headers in your requests to the MCP server.
ALLOWED_DOMAIN_PATTERN env variable
The ALLOWED_DOMAIN_PATTERN environment variable is used to specify a regex pattern for allowed API domains that the MCP server can connect to. When set, the server will validate the X-Saleor-API-URL header against this pattern. If not set, any domain is allowed. Patten must include escaping for special characters.
Example: https:\/\/.*\.saleor\.cloud\/graphql\/ - allows any subdomain of saleor.cloud and the /graphql/ path.
Integration with AI Assistants
Saleor MCP can be enabled in AI assistants that support integration with custom MCP servers using Streamable HTTP and setting the appropriate headers.
Below is the example configuration for VSCode / Copilot using mcp.json file:
{
"servers": {
"saleor-mcp": {
"type": "http",
"url": "https://mcp.saleor.app/mcp",
"headers": {
"X-Saleor-Auth-Token": "eyJhb...",
"X-Saleor-API-URL": "https://example.saleor.cloud/graphql/"
}
}
}
}
Development
This project uses ariadne-codegen to generate Saleor API client code from the GraphQL schema. See pyproject.toml for configuration.
To regenerate the client locally run:
ariadne-codegen
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.