PRTS MCP Server — Python 实现
明日方舟同人创作辅助 MCP Server，Python 版本。通过 stdio 传输接入 MCP 客户端（Claude Desktop、Claude Code、Chatbox 等），支持 Docker 部署。
提供 32 个 MCP 工具：PRTS 词条检索与页面结构、干员档案/语音/基础信息、剧情活动与台词、角色出场追踪、全文搜索、敌人图鉴、关卡查询、关卡敌人融合，以及物品/材料查询。完整清单见仓库根目录 README.md。
快速开始（Docker）
# 从仓库根目录构建（可选预置 bundled 数据，详见下方）
docker build -f python/Dockerfile -t prts-mcp .
# 运行（named volume 持久化游戏数据，推荐）
docker run -i --rm -v prts-mcp-data:/data/gamedata -v prts-mcp-levels:/data/gamedata-levels -v prts-mcp-storyjson:/data/storyjson prts-mcp
接入 MCP 客户端
{
"mcpServers": {
"prts_wiki": {
"command": "docker",
"args": ["run", "-i", "--rm", "-v", "prts-mcp-data:/data/gamedata", "-v", "prts-mcp-levels:/data/gamedata-levels", "-v", "prts-mcp-storyjson:/data/storyjson", "prts-mcp"]
}
}
}
请使用
docker run而非docker compose run。后者会向 stdio 流写入进度信息，污染 JSON-RPC 通道。
不使用 Docker（pip install）
pip install -e .
# 需指定游戏数据目录（GAMEDATA_PATH 设置后禁用 auto-sync）
GAMEDATA_PATH=/path/to/ArknightsGameData prts-mcp
数据机制
服务器启动时自动同步三类数据：
- 游戏表格数据（
gamedatavolume）：从 3aKHP/ArknightsGameData Release 下载zh_CN-excel.zip，其内容同步自 Kengxxiao/ArknightsGameData - 关卡战斗数据（
gamedata-levelsvolume）：从同一 Release 下载zh_CN-levels.zip，用于关卡实际出怪和关卡级敌人数值 - 剧情数据（
storyjsonvolume）：从 ArknightsStoryJson Releases 下载zh_CN.zip
镜像内置 bundled 数据作为网络不可用时的离线保底。
PyPI 包本身不内置 bundled 数据；直接
pip install prts-mcp时会在启动时自动同步，或使用GAMEDATA_PATH/STORYJSON_PATH指向你自己的本地数据。若GAMEDATA_PATH指向完整 ArknightsGameData 仓库根目录，内含的zh_CN/gamedata/levels会直接用于关卡战斗数据；否则默认在其相邻目录维护gamedata-levels。正式 Docker 镜像会由 CI 预置兜底数据。
详细文档
→ docs/deployment.md：完整部署方式、MCP 客户端配置、环境变量参考
1 maintainer
Metadata
1 maintainer
Release files for prts-mcp 1.7.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| prts_mcp-1.7.2.tar.gz | 99.7 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| prts_mcp-1.7.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 169.3 kB
Release files / prts_mcp-1.7.2.tar.gz
| Download URL | prts_mcp-1.7.2.tar.gz |
|---|---|
| Size | 99.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
343f3b0c16a1cca296c07b73557b695b5836cf05c9dee7aa4b8cb8bbfe00ef23
|
|
BLAKE2b-256 checksum How to use checksums |
c42985f3f1d0c939a7d3b8a787c12575f14b2085d39048fff1581c77d5fe4c89
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 26, 2026.
Transparency logRelease files / prts_mcp-1.7.2-py3-none-any.whl
| Download URL | prts_mcp-1.7.2-py3-none-any.whl |
|---|---|
| Size | 69.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
fa38596a0cdfb47cdc79410849f8d919ad146c1a6444e040d5b53d4453f5ad96
|
|
BLAKE2b-256 checksum How to use checksums |
5734d8a97f2a5a4ffd26ef573b79d747c6b9f64bde095cec4c833dc3c42086e9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 26, 2026.
Transparency log
