WatchBase MCP Server
An MCP server providing structured access to WatchBase's watch database, enabling applications to query comprehensive watch metadata including brands, collections, models, reference numbers, and technical details.
README
WatchBase MCP Server
An MCP (Model Context Protocol) server providing access to the WatchBase Data Feed API for querying watch metadata.
About WatchBase API
The WatchBase Data Feed API provides structured access to a comprehensive database of watch information, including brands, families (collections), specific watch models, reference numbers, technical details, and images. It allows developers to integrate detailed watch data into their applications. More information can be found on the WatchBase API Documentation.
Features
This MCP server exposes the following tools corresponding to the WatchBase API endpoints:
search: Search the database by brand name, family name, watch name, and reference number (matches whole words).search_refnr: Search the database by reference number (allows partial matches).list_brands: Retrieve a list of all watch brands in the database.list_families: Retrieve a list of all families (collections) for a given brand ID.list_watches: Retrieve a list of watches for a particular Brand ID and optionally Family ID. Can be filtered by update date.get_watch_details: Retrieve the full details (all data fields) for a particular watch by its WatchBase ID.
Prerequisites
- Node.js and npm: Required to install dependencies and run the server.
- WatchBase API Key: You need an API key from WatchBase. Visit the WatchBase API page to request access and obtain a key.
Installation
-
Clone the repository:
git clone https://github.com/watchdealer-pavel/watchbase-mcp.git cd watchbase-mcp -
Install dependencies:
npm install -
Build the server:
npm run buildThis command compiles the TypeScript source code into JavaScript, placing the output in the
build/directory (specificallybuild/index.js).
Configuration
The server requires your WatchBase API key to be provided via the WATCHBASE_API_KEY environment variable. You need to configure your MCP client (like Cline/Roo Code or the Claude Desktop App) to run this server and pass the environment variable.
Example Configuration:
Below are examples for common MCP clients. Remember to replace /path/to/your/watchbase-mcp/build/index.js with the actual absolute path to the compiled server file on your system, and YOUR_WATCHBASE_API_KEY with your real WatchBase API key.
Cline / Roo Code (VS Code Extension)
-
Open your VS Code settings for MCP servers. On macOS, this is typically located at:
~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json(Note: The exact path might vary based on your operating system and VS Code installation type. For Roo Code, replacesaoudrizwan.claude-devwithrooveterinaryinc.roo-cline) -
Add the following configuration block under the
mcpServerskey:"watchbase-mcp": { "command": "node", "args": ["/path/to/your/watchbase-mcp/build/index.js"], // <-- IMPORTANT: Replace with the ACTUAL absolute path to build/index.js "env": { "WATCHBASE_API_KEY": "YOUR_WATCHBASE_API_KEY" // <-- IMPORTANT: Replace with your WatchBase API Key }, "disabled": false, "autoApprove": [] // Or add specific tools you want to auto-approve }
Claude Desktop App
-
Open the Claude Desktop App configuration file. On macOS, this is typically located at:
~/Library/Application Support/Claude/claude_desktop_config.json(Note: The exact path might vary based on your operating system.) -
Add the following configuration block under the
mcpServerskey:"watchbase-mcp": { "command": "node", "args": ["/path/to/your/watchbase-mcp/build/index.js"], // <-- IMPORTANT: Replace with the ACTUAL absolute path to build/index.js "env": { "WATCHBASE_API_KEY": "YOUR_WATCHBASE_API_KEY" // <-- IMPORTANT: Replace with your WatchBase API Key }, "disabled": false, "autoApprove": [] // Or add specific tools you want to auto-approve }
Usage
Once configured, you can invoke the server's tools from your AI assistant using the use_mcp_tool command/tool.
search Example
<use_mcp_tool>
<server_name>watchbase-mcp</server_name>
<tool_name>search</tool_name>
<arguments>
{
"q": "priors court"
}
</arguments>
</use_mcp_tool>
search_refnr Example
<use_mcp_tool>
<server_name>watchbase-mcp</server_name>
<tool_name>search_refnr</tool_name>
<arguments>
{
"q": "P2/"
}
</arguments>
</use_mcp_tool>
list_brands Example
<use_mcp_tool>
<server_name>watchbase-mcp</server_name>
<tool_name>list_brands</tool_name>
<arguments>
{}
</arguments>
</use_mcp_tool>
list_families Example
<use_mcp_tool>
<server_name>watchbase-mcp</server_name>
<tool_name>list_families</tool_name>
<arguments>
{
"brand_id": 37
}
</arguments>
</use_mcp_tool>
list_watches Example
<use_mcp_tool>
<server_name>watchbase-mcp</server_name>
<tool_name>list_watches</tool_name>
<arguments>
{
"brand_id": 37,
"family_id": 279
}
</arguments>
</use_mcp_tool>
get_watch_details Example
<use_mcp_tool>
<server_name>watchbase-mcp</server_name>
<tool_name>get_watch_details</tool_name>
<arguments>
{
"id": 17289
}
</arguments>
</use_mcp_tool>
License
This MCP server project is licensed under the MIT License - see the LICENSE file for details.
Please also refer to WatchBase terms of service regarding API usage.
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.