MCP.so
登录

@tiberriver256/docs-to-mcp-cli

@Tiberriver256

关于 @tiberriver256/docs-to-mcp-cli

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

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

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is @tiberriver256/docs-to-mcp-cli?

@tiberriver256/docs-to-mcp-cli is a CLI tool that generates a self-contained, runnable MCP (Model Context Protocol) server from a collection of markdown documentation files. The generated server exposes documentation through specific tools (list_docs, get_doc, search_docs), enabling AI assistants that support MCP to browse, search, and retrieve documentation content.

How to use @tiberriver256/docs-to-mcp-cli?

Install globally via npm install -g @tiberriver256/docs-to-mcp-cli or use directly with npx. The basic command is docs-to-mcp-cli --docs <pattern> --packageName <name>. Required options are --docs (glob pattern for markdown files) and --packageName (name for the generated server). Optional flags include --outDir and --toolName. After generation, run the server with node dist/index.js.

Key features of @tiberriver256/docs-to-mcp-cli

  • Generates a self-contained, runnable MCP server from markdown docs
  • Provides three tools: list_docs, get_doc, and search_docs
  • Uses fuzzy matching for cross-document search
  • Supports custom tool names and output directories
  • Integrates with any MCP‑compatible AI assistant

Use cases of @tiberriver256/docs-to-mcp-cli

  • Allow an AI assistant to browse and retrieve full documentation content
  • Enable semantic search across a set of markdown files
  • Embed project or API documentation into AI‑powered workflows

FAQ from @tiberriver256/docs-to-mcp-cli

What tools does the generated MCP server provide?

The server provides three tools: list_docs (lists all 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 (defaults to dist).

What command-line options are available?

Options include --docs (required glob pattern), --packageName (required server name), --outDir (output directory, default "dist"), --toolName (optional name for the documented tool/package), and --version.

How can I use this with an AI assistant?

Once the generated MCP server is running, any AI assistant that supports the Model Context Protocol can connect to it and access your documentation for more accurate, contextual responses.

What version is the tool at?

The current version is 1.1.2 (see CHANGELOG.md for details).

常见问题

What tools does the generated MCP server provide?

The server provides three tools: list_docs (lists all 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 (defaults to `dist`).

What command-line options are available?

Options include `--docs` (required glob pattern), `--packageName` (required server name), `--outDir` (output directory, default "dist"), `--toolName` (optional name for the documented tool/package), and `--version`.

How can I use this with an AI assistant?

Once the generated MCP server is running, any AI assistant that supports the Model Context Protocol can connect to it and access your documentation for more accurate, contextual responses.

What version is the tool at?

The current version is 1.1.2 (see CHANGELOG.md for details).

评论

记忆与知识 分类下的更多 MCP 服务器