Docs To MCP Cli

@AzureDevOpsAPI

代码仓库

基本信息

分类

记忆与知识

许可证

MIT license

传输方式

stdio

作者

AzureDevOpsAPI

关于 Docs To MCP Cli

A CLI utility for turning your docs into a stdio MCP server

#docs-to-mcp-cli#cli-tool #mcp-server

Docs To MCP Cli 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "docs-to-mcp-cli-azuredevopsapi": {
      "command": "npx",
      "args": [
        "@tiberriver256/docs-to-mcp-cli",
        "--docs",
        "path/to/docs/**/*.md",
        "--packageName",
        "MyDocsServer"
      ]
    }
  }
}

Docs To MCP Cli 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。

概览

What is docs-to-mcp-cli?

A CLI tool that generates a self‑contained, runnable MCP (Model Context Protocol) server from markdown documentation files. It exposes the documentation via specific tools so AI assistants can browse, search, and retrieve full document content.

How to use docs-to-mcp-cli?

Install globally with npm install -g @tiberriver256/docs-to-mcp-cli or use directly with npx. Run docs-to-mcp-cli --docs <pattern> --packageName <n> (both required) and optionally specify --outDir and --toolName. A bundled server is created in the output directory; start it with node dist/index.js.

Key features of docs-to-mcp-cli

Generates a self‑contained MCP server from markdown files
Provides three tools: list_docs, get_doc, and search_docs
Supports fuzzy matching across all documents
Customizable output directory and tool/package name
Run the server with a single Node.js command

Use cases of docs-to-mcp-cli

Let an AI assistant browse and search your project’s markdown documentation
Give LLMs context‑aware access to API docs, guides, or internal wikis
Convert static documentation into a live tool for AI‑powered question answering

常见问题

What is the Model Context Protocol (MCP)?

MCP is an open standard that enables AI assistants to access external tools and data sources.

What tools does the generated server expose?

It creates three tools: `list_docs` (lists documents with previews), `get_doc` (retrieves full content by path), and `search_docs` (fuzzy search across all documents).

How do I run the generated server?

After generation, execute `node dist/index.js` from the output directory.

What arguments are required?

The `--docs` (glob pattern for markdown files) and `--packageName` (name of the MCP server) options are both required.

Can I change the output directory?

Yes, use the `--outDir` option; the default is `dist`.

记忆与知识分类下的更多 MCP 服务器

OpenLore

aakarim

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab