mcpField
S
storeport

storeport

Local
github.com/CloudCorpRecordsDeveloper Tools0Updated 2w ago

About storeport

storeport helps Shopify developers learn APIs, search documentation, inspect the GraphQL schema, and validate code blocks. It provides both a CLI and an MCP server, using Shopify’s public developer service without requiring a token or API key.

Key features

  1. 01Learn about Shopify APIs
  2. 02Search and fetch developer docs
  3. 03Inspect the Admin GraphQL schema
  4. 04Ask development questions
  5. 05Validate GraphQL and component code blocks

Use cases

  1. 01Find checkout extensibility documentation
  2. 02Learn about a Shopify API
  3. 03Look up fields on Product
  4. 04Check code blocks before shipping

MCP support

It runs as a stdio MCP server and exposes tools for API learning, documentation search and retrieval, schema introspection, developer questions, and code validation to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"cloudcorprecords-storeport": {
"command": "npx",
"args": [
"-y",
"@reneturcios/storeport"
]
}
}
}
Run commandnpx -y @reneturcios/storeport

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@reneturcios/storeport0.1.0
ocighcr.io/cloudcorprecords/storeport:0.1.0

Tools

7

Saved tool list · updated 1w ago

ParameterTypeRequiredDescription
apistringYesThe name of the Shopify API surface to learn (e.g. the API to return guided learning context for).
conversationIdstringNoOptional conversation identifier to continue an existing learning conversation.

Details

From the project README

storeport

storeport is a small companion for building on Shopify. Shopify's developer surface is broad — many APIs, a large GraphQL schema, and a lot of documentation — so storeport gathers the everyday developer tasks into one place: start learning an API with guided context, search the documentation and pull a full page when a chunk is not enough, look up types and fields in the Admin GraphQL schema, ask the developer assistant a direct question, and check GraphQL and component code blocks before they ship. One binary serves a command-line interface and a stdio MCP server.

No Shopify store token and no API key are required. The upstream is Shopify's public developer service, and storeport sends no authorization header. The base URL defaults to https://shopify.dev and can be overridden with the SHOPIFY_DEV_BASE_URL environment variable.

Install

npx @reneturcios/storeport search "metafields"

Or run the container image:

docker run -i ghcr.io/cloudcorprecords/storeport

The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.

CLI

storeport learn admin-graphql
storeport learn functions --conversation-id conv-1
storeport search "checkout extensibility"
storeport search webhooks --max 5
storeport docs https://shopify.dev/docs/apps/build/checkout
storeport docs /docs/api/admin-graphql
storeport introspect Product
storeport introspect Order --api-version 2025-10
storeport ask "How do I store extra product data?"
storeport validate-graphql '{ shop { name } }'
storeport validate-components '<s-page heading="Hi"></s-page>'

storeport --version

Each command prints the upstream JSON payload. Exit codes: 0 on success, 1 when a call fails (including an upstream API error), 2 for usage errors. Empty queries, prompts, content, and URLs are rejected before any request is made.

MCP server

One bin serves both faces. The mcp subcommand starts a stdio MCP server:

npx -y @reneturcios/storeport mcp

MCP client configuration:

{
  "mcpServers": {
    "storeport": {
      "command": "npx",
      "args": ["-y", "@reneturcios/storeport", "mcp"]
    }
  }
}

No env block is needed: the server is keyless.

Tools
ToolInputWhat it returns
learn_shopify_apiapi (required), conversationId (optional)The guided learning context for the named API.
search_docs_chunksquery (required), maxNumResults (optional)The most relevant documentation chunks.
fetch_full_docsurl (required)The full text of one documentation page; an absolute URL is fetched as-is, a path is joined to the base URL.
introspect_graphql_schemaquery (required), apiVersion (optional)Admin GraphQL types and fields matching the term.
prompt_shopify_dev_assistantprompt (required), conversationId (optional)The developer assistant's answer.
validate_graphql_codeblockscontent (required), apiVersion (optional)Validation results per GraphQL code block.
validate_component_codeblockscontent (required)Validation results for Shopify component code blocks.

All calls go to the Shopify developer service under the configured base URL (default https://shopify.dev). This build covers a core subset of the documented developer surface: Liquid/theme codeblock validation, component validation for other frameworks, and docs update/feedback tools are not included.

Development

npm install
npm run build   # tsc -> dist/
npm test        # node test runner over test/*.test.ts, no network (fake fetch fixtures)
npm run dev     # run the CLI from source via tsx

License

MIT — see LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.