songsterr-mcp
Fetch Songsterr tabs and transpose them between tunings and string counts, outputting ASCII or Guitar Pro files.
README
songsterr-mcp
MCP server for fetching Songsterr tabs and transposing them between tunings and string counts — e.g. taking a song tabbed for 6-string C standard and re-fingering it, pitch-perfect, for a 7-string in B standard.
Status: working, pending live API verification. The transposition engine and the full Guitar Pro pipeline (parse → re-finger → ASCII / .gp5 export) are implemented and covered by tests, including an end-to-end GP5 round-trip. The Songsterr client uses a mix of documented-legacy and unofficial endpoints that still need verification against the live site (see below).
Tools
| Tool | Purpose |
|---|---|
songsterr_search_songs |
Find songs by title/artist pattern |
songsterr_get_tab |
Download a song's Guitar Pro source (cached), list tracks + tunings |
songsterr_transpose |
Re-finger a track onto a new tuning/string count; ASCII or .gp5 out |
songsterr_list_tunings |
Enumerate tuning presets |
Typical flow: search → get_tab (pick a track) → transpose with
target_tuning="b_standard_7" → read the ASCII or open the written .gp5.
semitone_shift changes actual key; 0 preserves the original pitch across the
tuning change.
Install & run
pip install -e .
python -m songsterr_mcp.server # stdio transport
Claude Desktop / Claude Code config:
{
"mcpServers": {
"songsterr": { "command": "python", "args": ["-m", "songsterr_mcp.server"] }
}
}
Tests: pytest tests/
Architecture
src/songsterr_mcp/
├── server.py # FastMCP tool definitions (thin; no business logic)
├── client.py # Songsterr HTTP client + on-disk cache (~/.cache/songsterr_mcp)
├── gp_io.py # pyguitarpro <-> engine model adapter; ALL string-number
│ # flipping (GP is high->low, engine is low->high) lives here
├── refinger.py # the engine: pitch decode -> candidates -> beam search
├── tuning.py # presets, note<->MIDI, tuning spec parsing
└── ascii_tab.py # monospace tab rendering
The engine never touches Guitar Pro objects or HTTP — it operates on a neutral
Beat/Note model, so it's independently testable and reusable (e.g. against
alphaTex or MusicXML sources later). See docs/ALGORITHM.md for the full
re-fingering algorithm, cost model, and known limitations.
Songsterr API caveats
- Legacy REST endpoints (
/a/ra/songs.json?pattern=) are publicly documented, keyless, and stable. - The modern endpoints (
/api/songs,/api/meta/{id}/revisions, and the revisionsourceURL pointing at the underlying Guitar Pro file) are unofficial — they power Songsterr's own player and can change without notice.client.pyfalls back to legacy where possible and fails with inspectable errors elsewhere. - Songsterr permits non-commercial API use; commercial use requires their approval. This project caches downloads and sends an identifying User-Agent — keep it that way.
License
GPL-3.0 — free software in the OSI/FSF sense, commercial use included.
Note the code license and the API terms are separate things: this code is GPL, but Songsterr's API itself permits only non-commercial use without their approval (see caveats above). Likewise, tab content fetched through this tool is copyrighted musical composition belonging to its rights holders; this tool is for personal practice use.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。