What is MCP and how does this server use it?
MCP (Model Context Protocol) is a standard for connecting LLMs to external tools and data sources. This server implements an MCP endpoint so that Claude Desktop can call the Science Museum Group API.
@opensourcedev90s
Basic information
MCP Server for the UK Science Museum Group
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"uk-science-museum-group-mcp": {
"command": "uv",
"args": [
"venv"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A Python MCP (Model Context Protocol) server that enables large language models, such as Claude, to fetch data from the UK Science Museum Group’s Collections Online API. It is designed for Claude Desktop on macOS and Windows.
Install UV (a Python package manager) on macOS or Windows, then edit your Claude Desktop configuration file (claude_desktop_config.json) to add the server entry shown in the README. After restarting Claude Desktop, you can query the museum’s collections directly through Claude.
MCP (Model Context Protocol) is a standard for connecting LLMs to external tools and data sources. This server implements an MCP endpoint so that Claude Desktop can call the Science Museum Group API.
You need Python and UV installed. The server is distributed as a Python package (`science-museum-mcp`) and is executed via `uvx`. No additional API key or authentication is required for the public collection API.
All data is retrieved in real‑time from the UK Science Museum Group’s official Collections Online API (documented at their GitHub wiki). The server does not store or cache any data locally.
The READTE only demonstrates configuration for Claude Desktop. The server follows the MCP standard, so in principle it may work with other hosts, but no other integrations are documented.
Install UV, then add the following to your `claude_desktop_config.json`: `{ "mcpServers": { "scienceMuseum": { "command": "uvx", "args": ["science-museum-mcp"] } } }`. Detailed paths for macOS and Windows are provided in the README.

Build custom POS apps with your AI agent. Final's MCP server lets developers scaffold checkout flows, adapt vetted screen blueprints for counter POS, self-checkout kiosks, restaurant ordering and payment terminals, previ

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

The elmah.io MCP server allows AI assistants to interact directly with your error logs, deployments, and organization statistics. Debug production issues faster than ever before.
Mobbin MCP connects your AI agents to 600,000+ real product screens, so what they build starts with what already works.
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.
Comments