McMaster-Carr MCP Server
Enables searching and retrieving detailed product specifications from McMaster-Carr using part numbers or search queries.
README
ABOUTME: Documentation for McMaster-Carr MCP server.
ABOUTME: Covers installation, configuration, and usage.
McMaster-Carr MCP Server
MCP server for searching and looking up product information from McMaster-Carr.
Uses SeleniumBase UC mode to extract product data from JavaScript-rendered pages.
Features
- Product Lookup: Get detailed specs (10-35+ fields) for any McMaster-Carr part number
- Search: Search for products and get part numbers from results
- URL Generation: Generate McMaster URLs without fetching (fast, no browser)
- Cookie Persistence: Browser profile saved for faster subsequent requests
Installation
cd tools/mcmaster-mcp
python -m venv .venv
source .venv/bin/activate
pip install -e .
Or install dependencies directly:
pip install mcp seleniumbase beautifulsoup4
Usage
Run the server directly
python server.py
Claude Code configuration
Add to ~/.claude.json (or your MCP config):
{
"mcpServers": {
"mcmaster-carr": {
"command": "python",
"args": ["/path/to/radiatron/tools/mcmaster-mcp/server.py"]
}
}
}
Available Tools
mcmaster_get_product
Get detailed product information by part number.
Input:
{
"part_number": "47865K23"
}
Returns:
- Product name
- 10-35+ specifications (material, size, pressure ratings, thread type, etc.)
- URL to product page
Example output:
{
"part_number": "47865K23",
"name": "Brass Body On/Off Valve, with Lever Handle, 1/2 NPT Female, 32.3 Cv",
"url": "https://www.mcmaster.com/47865K23",
"specs": {
"Pipe Size": "1/2",
"Flow Coefficient (Cv)": "32.3",
"Maximum Pressure": "600 psi @ 100° F",
"Body Material": "Brass",
"Valve Type": "Ball",
"Thread Type": "NPT"
}
}
mcmaster_search
Search McMaster-Carr and get products matching the query.
The search automatically navigates through McMaster's category structure to find actual product listings with part numbers and names.
Input:
{
"query": "ball valve brass"
}
Returns: List of products with part numbers and names (up to 50).
{
"query": "ball valve brass",
"count": 22,
"results": [
{"part_number": "47865K23", "name": "Threaded On/Off Valves", "url": "..."},
{"part_number": "4373K53", "name": "Diverting Valves", "url": "..."},
{"part_number": "8151N11", "name": "Socket-Connect On/Off Valves", "url": "..."}
]
}
mcmaster_url
Generate McMaster URLs without fetching. Fast, no browser needed.
Input (product):
{
"part_number": "47865K19"
}
Input (search):
{
"search_query": "stainless steel bolt"
}
How It Works
- SeleniumBase UC Mode - Undetected Chromium driver bypasses bot detection
- Visible Browser - McMaster blocks headless browsers, so a Chrome window briefly appears
- Cookie Persistence - Browser profile saved to
~/.mcmaster-browserfor faster subsequent requests - BeautifulSoup - Parses spec tables from rendered HTML
Limitations
- Visible browser window: McMaster detects headless browsers, so a Chrome window briefly appears during requests
- First request slower: ~5-8 seconds for browser startup, subsequent requests ~3-5 seconds
- CSS class changes: May break if McMaster updates their class naming conventions
Files
server.py- MCP server entry pointbrowser.py- SeleniumBase browser automationagent.py- Product search agent with requirement parsing (CLI tool)mcmaster.py- Legacy CDP-mode client (deprecated, kept for reference)
Development
Run tests:
python test_agent.py
python test_search.py
Test the browser directly:
python -c "from browser import McMasterBrowser; b = McMasterBrowser(); b.start(); print(b.get_product('47865K23'))"
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.