Javadoc Mcp

@loong95

About Javadoc Mcp

让 AI 助手能够通过 Maven 坐标浏览 JavaDoc 文档

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "javadoc": {
      "command": "npx",
      "args": [
        "-y",
        "javadoc-mcp"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Javadoc Mcp?

Javadoc Mcp is a Model Context Protocol (MCP) server that allows AI assistants to browse JavaDoc documentation using Maven coordinates. It is designed for developers who need programmatic access to Java library documentation via an AI or CLI tool.

How to use Javadoc Mcp?

Install via npx -y javadoc-mcp or npm install -g javadoc-mcp, then configure your MCP client (e.g., Claude Code or Claude Desktop) with the appropriate command and arguments in settings.json or claude_desktop_config.json. After setup, tools are automatically available to the AI assistant.

Key features of Javadoc Mcp

Five MCP tools for browsing JavaDoc: list_packages, list_classes, get_class, get_member, and search.
Reads from the local Maven repository (~/.m2/repository) or auto-fetches missing -javadoc.jar files.
Uses cheerio for HTML parsing and adm-zip to read directly from JARs without extracting to disk.
Implemented in TypeScript with the @modelcontextprotocol/sdk.

Use cases of Javadoc Mcp

An AI assistant looks up a class’s method signatures and documentation while writing Java code.
A developer searches for a specific type or member across multiple Java libraries.
Automated tooling browses the package structure of a Maven artifact to generate API summaries.

FAQ from Javadoc Mcp

What are the system requirements?

Node.js 18+ is required, and the mvn command must be available in PATH.

Where are JavaDoc JARs stored locally?

Javadoc Mcp uses the local Maven repository, typically located at ~/.m2/repository, or the path specified in ~/.m2/settings.xml under <localRepository>.

How do I refresh the documentation for a library?

Delete the corresponding *-javadoc.jar from your local Maven repository for that artifact; the server will fetch it again on the next invocation.

How is Javadoc Mcp configured with MCP clients?

Add a server entry to your MCP client configuration (e.g., ~/.claude/settings.json or claude_desktop_config.json) with "command": "npx" and "args": ["-y", "javadoc-mcp"], or "command": "javadoc-mcp" if globally installed.

Does Javadoc Mcp support authentication for private Maven repositories?

The README does not mention any authentication mechanisms; it assumes public Maven Central or repositories accessible via standard Maven settings.

Frequently asked questions

What are the system requirements?

Node.js 18+ is required, and the `mvn` command must be available in `PATH`.

Where are JavaDoc JARs stored locally?

Javadoc Mcp uses the local Maven repository, typically located at `~/.m2/repository`, or the path specified in `~/.m2/settings.xml` under `<localRepository>`.

How do I refresh the documentation for a library?

Delete the corresponding `*-javadoc.jar` from your local Maven repository for that artifact; the server will fetch it again on the next invocation.

How is Javadoc Mcp configured with MCP clients?

Add a server entry to your MCP client configuration (e.g., `~/.claude/settings.json` or `claude_desktop_config.json`) with `"command": "npx"` and `"args": ["-y", "javadoc-mcp"]`, or `"command": "javadoc-mcp"` if globally installed.

Does Javadoc Mcp support authentication for private Maven repositories?

The README does not mention any authentication mechanisms; it assumes public Maven Central or repositories accessible via standard Maven settings.

Comments

Basic information

More Other MCP servers

Peekaboo MCP – lightning-fast macOS screenshots for AI agents

steipete

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

4.8K