Shelby docs MCP
A read-only MCP server that provides searchable access to the Shelby documentation bundle for MCP-compatible clients. It enables users to search, list, and read documentation pages directly within AI tools and IDEs.
README
Shelby docs MCP
A lightweight, read-only MCP server that exposes Shelby documentation as searchable tools for MCP-compatible clients like Claude Code, Codex, Cursor, VS Code, and Gemini CLI.
This project is a docs-only server. It does not write data, talk to Shelby RPC endpoints, or modify anything in the network.
Docs source
The server loads the full Shelby LLM docs bundle:
It parses that bundle into page-level chunks using the native Shelby format:
# Page Title (/path)
Page content...
# Next Page (/next-path)
Next page content...
Quickstart for Claude Code
Add the MCP server with npx:
claude mcp add --transport stdio shelby-docs -- npx -y github:Jr-kenny/shelby-mcp
Then start Claude Code:
claude
Inside Claude Code, run:
/mcp
You should see the shelby-docs server and its tool endpoints listed.
Quickstart for Cursor (per-project)
Create .cursor/mcp.json and add:
{
"mcpServers": {
"shelby-docs": {
"command": "npx",
"args": ["-y", "github:Jr-kenny/shelby-mcp"]
}
}
}
[!TIP] If Cursor does not recognize
mcpServersin your version, trymcp_serversas the top-level key instead.
Quickstart for VS Code (per-workspace)
Add this to .vscode/mcp.json:
{
"servers": {
"shelby-docs": {
"type": "stdio",
"command": "npx",
"args": ["-y", "github:Jr-kenny/shelby-mcp"]
}
},
"inputs": []
}
Quickstart for Gemini CLI
Add the MCP server globally:
gemini mcp add --scope user shelby-docs npx -y github:Jr-kenny/shelby-mcp
Confirm it is registered:
gemini mcp list
Quickstart for Codex
Add the MCP server with the Codex CLI:
codex mcp add shelby-docs -- npx -y github:Jr-kenny/shelby-mcp
Confirm it is registered:
codex mcp list
Alternatively, add this to your Codex MCP config:
[mcp_servers.shelby-docs]
command = "npx"
args = ["-y", "github:Jr-kenny/shelby-mcp"]
Then restart Codex if needed so it reloads the MCP config.
Quickstart from source
If you want to run the repository locally from source:
-
Clone the repo:
git clone https://github.com/Jr-kenny/shelby-mcp cd shelby-mcp -
Install dependencies and build:
npm install npm run build -
Run the local entrypoint:
node /absolute/path/to/shelby-mcp/dist/cli.js
Then substitute that node .../dist/cli.js command in any MCP client config if you prefer source-based usage over npx.
Repository
GitHub repository:
Tool endpoints
-
search_shelby_docsSearches the Shelby documentation bundle and returns ranked matches with IDs and snippets. -
read_shelby_docReads a page by exact path, title, URL, page ID, or fuzzy query. -
get_shelby_doc_chunkReads a specific page by the exact chunk ID returned from search results. -
list_shelby_doc_pagesLists available parsed pages and supports filtering by path or title text.
Project structure
| File/Folder | Purpose |
|---|---|
src/index.ts |
MCP server setup, tool registration, and stdio startup |
src/cli.ts |
CLI entry point that starts the server |
src/shelbyDocs.ts |
Shelby docs loading, parsing, search, and formatting helpers |
dist/ |
Compiled JavaScript output generated by npm run build |
package.json |
Dependencies, scripts, package metadata, and CLI registration |
tsconfig.json |
TypeScript compiler settings |
README.md |
Usage and setup instructions |
How it's built
This MCP server is a lightweight TypeScript implementation built on the official MCP SDK.
Core components
- Built on
@modelcontextprotocol/sdk - Uses
StdioServerTransportfor local MCP clients - Uses
zodto validate tool inputs - Fetches Shelby docs from the official
llms-full.txtbundle at startup - Parses the bundle into page chunks using Shelby's
# Title (/path)format - Uses deterministic keyword scoring over titles, paths, URLs, and body text
Configuration
Optional environment variables:
SHELBY_DOCS_URL: alternate docs bundle URLSHELBY_DOCS_TIMEOUT_MS: HTTP timeout in milliseconds, default15000
Fork this for your own docs
This repo is a good base if you want to publish other docs-only MCP servers backed by a single llms-full.txt style bundle.
-
Update
package.json:{ "name": "your-docs-mcp", "description": "Docs-only MCP server for YourProduct documentation" } -
Update the docs URL in
src/shelbyDocs.ts:const DEFAULT_DOCS_URL = "https://your-domain.com/llms-full.txt"; -
Update the server name in
src/index.ts:name: "your-docs-mcp" -
Build and publish:
npm install npm run build
Local development
This section is only for working on the MCP server itself.
npm install
npm run build
npm run check
npm start
npm run check verifies that the server can fetch and parse the live Shelby docs bundle.
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。
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。
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。
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。