mechanic-mcp
Enables searching, fetching, and customizing Mechanic tasks and documentation for Shopify automation. Provides offline access to bundled task library and docs with tools for task code, docs content, and similar task suggestions.
README
mechanic-mcp
Mechanic MCP server for the task library and docs. Built for writing and customizing Mechanic tasks (Shopify automation app: https://apps.shopify.com/mechanic). Offline by default (bundled data), serving public URLs for tasks (https://tasks.mechanic.dev) and docs (https://learn.mechanic.dev).
User guide
- Requirements: Node.js 18+, MCP-capable client (Cursor, Claude Desktop, Codex, Gemini CLI, etc.).
- What you can ask: find tasks; fetch task code (subscriptions + script/JS blocks); find docs; suggest similar tasks; get doc content; help writing or customizing Mechanic tasks.
- Setup (use
npx @lightward/mechanic-mcp@latest):- Cursor:
{ "mcpServers": { "mechanic-mcp": { "command": "npx", "args": ["-y", "@lightward/mechanic-mcp@latest"] } } } - Claude Desktop:
{ "mcpServers": { "mechanic-mcp": { "command": "npx", "args": ["-y", "@lightward/mechanic-mcp@latest"] } } } - Codex (
~/.codex/config.toml):[mcp_servers.mechanic-mcp] command = "npx" args = ["-y", "@lightward/mechanic-mcp@latest"] - Gemini CLI: same JSON as Cursor/Claude.
- Cursor:
- Tools:
search_tasks: returns public URL, tags, subscriptions/subscriptions_template, options.search_docs: returns public URL/sourceUrl.get_task(tasks only): script + subscriptions + options + JS blocks; not full JSON.get_doc(docs only): full markdown.similar_tasks: related tasks by tags/subscriptions/title.refresh_index: rebuild (not needed for packaged data).
- Usage notes: cite public URLs (no local paths/.md); prefer GraphQL in code; when sharing code, return subscriptions + script/JS (relevant bits), not full JSON.
For maintainers
- Bundled data:
dist/data/index.json.gz,records.json.gz,manifest.json(users don’t need source repos). - Regenerate (if needed):
MECHANIC_DOCS_PATH=/path/to/mechanic-docs MECHANIC_TASKS_PATH=/path/to/mechanic-tasks npm run build:data npm run build - Tests:
npm run test:smoke,npm run test:smoke-doc,npm run test:smoke-task. - Publish: bump version,
npm publish(use--access publicfor scoped packages).
Env (optional)
MECHANIC_DATA_PATH(defaultdist/data),MECHANIC_DOCS_PATH,MECHANIC_TASKS_PATH, repo URLs/branches, sync interval.
Runtime
- Loads bundled index/records from
MECHANIC_DATA_PATH;refresh_indexrebuilds if you opt in. Stdio transport; TF-IDF search with fuzzy + pagination; no network calls for search/resources.
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.