MCP Servers

isaac-wiki-mcp

Provides full class documentation for the Binding of Isaac modding API, enabling AI assistants to access complete class pages with methods, enums, and tutorials to avoid hallucination.

README

isaac-wiki-mcp

以撒的结合：忏悔(+) 模组 API 文档的 MCP 知识库服务器。

采用 llmwiki 架构 —— 文件系统原生的 markdown 页面 + [[wikilinks]] 交叉引用。纯 Python 实现，零 ML 依赖，只依赖 loguru 一个包。

解决了什么问题

用 AI 写以撒模组时，LLM 会编造不存在的 API 方法名和参数。这个项目把 72 个类、1,554 个方法的完整 API 文档做成了可搜索的知识库，让 AI 能查到完整的类页面（不是碎片化的 chunk），避免幻觉。

快速上手

pip install isaac-wiki-mcp

然后在 Claude Code 的 MCP 配置里加上（~/.claude/mcp.json）：

{
  "mcpServers": {
    "isaac-wiki": {
      "command": "uvx",
      "args": ["isaac-wiki-mcp"]
    }
  }
}

也可以用 Docker：

{
  "mcpServers": {
    "isaac-wiki": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "ghcr.io/你的用户名/isaac-wiki-mcp"]
    }
  }
}

MCP 工具

工具	功能
`wiki_search`	全文搜索，返回完整页面内容（不是片段）
`wiki_read`	按名称读取完整类文档，如 `EntityPlayer`
`wiki_list`	按分类列出页面（classes / enums / tutorials）
`wiki_stats`	查看知识库统计数据

命令行

isaac-wiki search "player health" --category classes
isaac-wiki read EntityPlayer
isaac-wiki list --category classes
isaac-wiki stats
isaac-wiki build          # 从数据源重建 wiki

数据规模

分类	数量
类	71
方法	1,554
枚举	81
教程	20
总页面	173

每个类页面包含：概述、继承链、关联类型（带 [[wikilinks]]）、所有方法的签名、DLC 兼容标记、使用场景。

架构

src/isaac_wiki/
  wiki_builder.py   — 数据清洗 + JSON → wiki markdown 转换
  wiki_engine.py    — 全文搜索 + 页面读取（纯 Python）
  facade.py         — 对外 API 层（永不抛异常）
  server.py         — MCP stdio 服务器（4 个工具）
  cli.py            — 命令行工具

wiki/               — 生成的 markdown 页面（~1.3MB）
  classes/          — 71 个类页面，含 [[wikilinks]]
  enums/            — 81 个枚举参考页
  tutorials/        — 20 个教程
  index.md          — 全局导航
  llms.txt          — AI 可消费的摘要（llmstxt.org 规范）

data/               — 源数据（wiki_builder 的输入）

开发

pip install -e ".[dev]"
pytest tests/ -v

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.

Official

Featured

TypeScript

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.

Official

Featured

Local

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.

Official

Featured

TypeScript

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.

Official

Featured

Python

E2B

Using MCP to run code via e2b.

Official

Featured

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

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.

Official

Featured

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official

Featured