osu-mcp
MCP server that exposes the osu! API v2 as tools, allowing natural language queries about osu! profiles, beatmaps, rankings, and more.
README
<!-- mcp-name: io.github.Osyanne/osu-mcp -->
osu-mcp
osu-mcp is a Model Context Protocol (MCP) server that exposes the osu! API v2 as tools for Claude Desktop and other MCP clients. Ask Claude about your osu! profile, compare players, search beatmaps, browse rankings — all in natural language.
Quickstart
1. Install
uv tool install osu-mcp
# or
pip install osu-mcp
2. Get osu! API credentials
- Go to https://osu.ppy.sh/home/account/edit
- Scroll to OAuth, click New OAuth Application
- Name: anything (e.g., "Claude Desktop"); Callback URL: leave blank.
- Copy the Client ID and Client Secret.
3. Configure credentials
Option A — environment variables (recommended):
export OSU_CLIENT_ID=12345
export OSU_CLIENT_SECRET=your-client-secret
Option B — config file at ~/.config/osu-mcp/config.toml (Linux/Mac) or %APPDATA%\osu-mcp\config.toml (Windows):
client_id = 12345
client_secret = "your-client-secret"
4. Wire up Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"osu": {
"command": "uvx",
"args": ["osu-mcp"],
"env": {
"OSU_CLIENT_ID": "12345",
"OSU_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Restart Claude Desktop. You should see "osu" in the MCP servers list.
Available tools (12)
| Tool | Description |
|---|---|
get_user_summary |
Profile + stats; optionally embed recent/best/firsts scores |
compare_users |
Side-by-side comparison of 2-5 users |
get_user_scores |
List a user's best/recent/firsts scores |
get_score_details |
Full attributes of a specific score |
search_beatmaps |
Search beatmapsets with filters (mode, status, difficulty, length, BPM) |
get_beatmap_details |
Full attributes of a beatmap (AR/OD/CS/HP, BPM, max combo) |
get_beatmap_scores |
Top scores on a beatmap, filterable by mods |
get_beatmapset |
Full beatmapset with all difficulties |
get_rankings |
pp/score/charts rankings, global or by country |
get_country_top |
Top N players of a country in pp ranking |
get_news_posts |
Recent osu! news posts |
get_seasonal_backgrounds |
Active seasonal backgrounds |
Full reference: docs/tools.md.
Examples
In Claude Desktop, try:
"Show me peppy's osu! stats"
"Compare Cookiezi and WhiteCat on accuracy and pp"
"What are the top 10 osu! players from Ecuador?"
"Find me some 200 BPM streamy ranked maps"
Development
git clone https://github.com/Osyanne/osu-mcp.git
cd osu-mcp
uv sync
uv run pytest # unit + smoke
uv run pytest -m integration # integration (needs real creds)
uv run ruff check .
uv run mypy --strict src/
License
MIT — see LICENSE.
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.