prts-mcp
Arknights PRTS Wiki MCP Server — queries the PRTS Wiki API for full-text search and article extraction, and serves auto-synced operator archives, voice lines, and story/event scripts from game data. Designed for fan-creation AI agents that need accurate lore, character profiles, and in-character dialogue references.
README
PRTS MCP Server
<a id="english"></a>
English
An MCP Server for Arknights fan creation (同人創作) AI agents. Powered by the PRTS Wiki MediaWiki API and auto-synced operator game data, it gives any MCP-compatible client — Claude Desktop, Claude Code, Chatbox, and more — live access to lore, operator archives, and voice lines from the world of Terra.
Implementations
This repository contains two independent implementations for different deployment scenarios:
| Directory | Language | Transport | Use case |
|---|---|---|---|
python/ |
Python 3.10+ | stdio | Local Claude Desktop / Claude Code, Docker |
ts/ |
TypeScript / Node.js | Streamable HTTP | Self-hosted server, remote HTTP access |
Tools
Both implementations expose the same tool set:
| Tool | Description |
|---|---|
search_prts(query, limit) |
Search PRTS Wiki by keyword, returns matching article titles |
read_prts_page(page_title) |
Fetch the plain-text content of a PRTS Wiki article |
get_operator_archives(operator_name) |
Retrieve operator archive records (Chinese name) |
get_operator_voicelines(operator_name) |
Retrieve operator voice lines (Chinese name) |
get_operator_basic_info(operator_name) |
Retrieve basic operator profile: class, rarity, faction, recruit tags, talents (Chinese name) |
list_story_events(category?) |
List story events; optional filter: main (main story) or activities |
list_stories(event_id) |
List chapters of an event in official order |
read_story(story_key, include_narration) |
Read full dialogue for a single chapter |
read_activity(event_id, include_narration, page, page_size) |
Read a complete activity's transcript, with pagination |
Quick Start
Data Sources
- PRTS Wiki API (
https://prts.wiki/api.php) — lore articles, faction info, world-building entries - ArknightsGameData (
Kengxxiao/ArknightsGameData) — operator archives, voice lines, base stats - ArknightsStoryJson (
3aKHP/ArknightsStoryJson) — parsed story dialogue, auto-synced from GitHub Releases (zh_CN.zip)
Game data lives in the gamedata volume. Story data lives in the storyjson volume. Both are auto-synced on server startup.
<a id="中文"></a>
中文
明日方舟同人创作辅助 MCP Server。通过 PRTS Wiki API 和自动同步的干员数据，为 MCP 客户端（Claude Desktop、Claude Code、Chatbox 等）提供泰拉世界观检索与干员资料查询能力。
实现版本
本仓库包含两个独立实现，适用于不同的部署场景：
| 目录 | 语言 | 传输方式 | 适用场景 |
|---|---|---|---|
python/ |
Python 3.10+ | stdio | Claude Desktop / Claude Code 本地接入、Docker |
ts/ |
TypeScript / Node.js | Streamable HTTP | 个人服务器部署，供他人通过 HTTP 调用 |
工具集
两个实现提供相同的工具集：
| 工具 | 说明 |
|---|---|
search_prts(query, limit) |
关键词搜索 PRTS 维基词条，返回匹配标题列表 |
read_prts_page(page_title) |
读取指定词条的纯文本内容 |
get_operator_archives(operator_name) |
获取干员档案资料（中文名） |
get_operator_voicelines(operator_name) |
获取干员语音记录（中文名） |
get_operator_basic_info(operator_name) |
获取干员基本信息：职业、稀有度、所属、招募标签、天赋（中文名） |
list_story_events(category?) |
列出剧情活动，可选过滤：main（主线）或 activities（活动） |
list_stories(event_id) |
列出指定活动的章节（按官方顺序） |
read_story(story_key, include_narration) |
读取单章完整台词 |
read_activity(event_id, include_narration, page, page_size) |
读取整个活动的完整剧情，支持分页 |
快速开始
数据源
- PRTS Wiki API (
https://prts.wiki/api.php) — 世界观词条、阵营设定 - ArknightsGameData (
Kengxxiao/ArknightsGameData) — 干员档案、语音记录、基础信息 - ArknightsStoryJson (
3aKHP/ArknightsStoryJson) — 剧情台词解析数据，从 GitHub Releases 自动同步（zh_CN.zip）
干员数据存放在 gamedata volume，剧情数据存放在 storyjson volume，均在服务器启动时自动同步。
License
MIT
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.