原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

JVM Source Lens

作者:Sintexer版本 1.16.0i★ –i在你的电脑上运行
注册名称io.github.Sintexer/jvmsrc

安装

概览

作者提供的说明(英文原文)

Gradle-accurate JVM classpath; fetch Java source, signatures, and class structure for agents.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 其他

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 1 项
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 需要你自己填写: JVMSRC_ALLOWED_ROOTS, JVMSRC_CACHE_ROOT, JVMSRC_LOG_DIR, JVMSRC_MAX_SOURCE_OUTPUT_CHARS, JVMSRC_GRADLE_TIMEOUT_MS, JVMSRC_CFR_PATH

你需要

  • npm已安装 Node.js(用于 npx 命令)

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "jvmsrc": {
      "command": "npx",
      "args": [
        "-y",
        "jvmsrc",
        "mcp"
      ],
      "env": {
        "JVMSRC_ALLOWED_ROOTS": "your-value",
        "JVMSRC_CACHE_ROOT": "your-value",
        "JVMSRC_LOG_DIR": "your-value",
        "JVMSRC_MAX_SOURCE_OUTPUT_CHARS": "your-value",
        "JVMSRC_GRADLE_TIMEOUT_MS": "your-value",
        "JVMSRC_CFR_PATH": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add jvmsrc --env JVMSRC_ALLOWED_ROOTS=your-value --env JVMSRC_CACHE_ROOT=your-value --env JVMSRC_LOG_DIR=your-value --env JVMSRC_MAX_SOURCE_OUTPUT_CHARS=your-value --env JVMSRC_GRADLE_TIMEOUT_MS=your-value --env JVMSRC_CFR_PATH=your-value -- npx -y jvmsrc mcp

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "jvmsrc": {
      "command": "npx",
      "args": [
        "-y",
        "jvmsrc",
        "mcp"
      ],
      "env": {
        "JVMSRC_ALLOWED_ROOTS": "your-value",
        "JVMSRC_CACHE_ROOT": "your-value",
        "JVMSRC_LOG_DIR": "your-value",
        "JVMSRC_MAX_SOURCE_OUTPUT_CHARS": "your-value",
        "JVMSRC_GRADLE_TIMEOUT_MS": "your-value",
        "JVMSRC_CFR_PATH": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "jvmsrc": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "jvmsrc",
        "mcp"
      ],
      "env": {
        "JVMSRC_ALLOWED_ROOTS": "your-value",
        "JVMSRC_CACHE_ROOT": "your-value",
        "JVMSRC_LOG_DIR": "your-value",
        "JVMSRC_MAX_SOURCE_OUTPUT_CHARS": "your-value",
        "JVMSRC_GRADLE_TIMEOUT_MS": "your-value",
        "JVMSRC_CFR_PATH": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上,无需账户。

需要你填写的值

  • JVMSRC_ALLOWED_ROOTS env
    Optional comma-separated absolute paths; only these project roots are allowed.
  • JVMSRC_CACHE_ROOT env
    Optional absolute path for resolution and decompile caches (default: OS cache dir).
  • JVMSRC_LOG_DIR env
    Optional absolute path for failure diagnostic logs.
  • JVMSRC_MAX_SOURCE_OUTPUT_CHARS env
    Max characters returned for full-file source (default 524288).
  • JVMSRC_GRADLE_TIMEOUT_MS env
    Gradle resolution subprocess timeout in milliseconds.
  • JVMSRC_CFR_PATH env
    Optional path to a custom CFR JAR for decompilation.

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 Sintexer 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 32684 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 32684 个服务器的 35% 更新
  • 基础检查结果等于或优于此分类中其他 32684 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

JVM Source Lens 安全吗?

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(1.16.0)于2个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。

有什么可以替代它?

同一分类中有:Spec Driven Development, Remote Desktop Commander, Master CSS

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Spec Driven Development

作者:formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新
安装

Remote Desktop Commander

作者:desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211前天更新
安装

Master CSS

作者:master-co

Inspect Master CSS classes, generated CSS, and project stylesheets from your AI client.

在你的电脑上运行今天更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

jvmsrc — Give your coding agent a Java IDE

An MCP server and CLI that gives your coding agent the one thing it's missing on JVM codebases: the actual classpath.


The Problem

You use an IDE to write Java. Your coding agent doesn't have one.

When your agent hits an unfamiliar library type — say, a superclass from a proprietary internal library — it spends 25+ turns walking ~/.gradle/caches, opening JARs by hand with jar tf, picking one by guesswork, and trying to answer a question your IDE would answer in one keystroke: *does this superclass have a public utility method called X?*

The Solution

jvmsrc queries your build tool (Gradle) for *this project's* resolved classpath, then hands your agent real source, real signatures, and real structure — for the exact version your build actually uses.

  • As an MCP server – Connect to Claude Code, Cursor, Windsurf, or any other MCP host and equip your agent with six purpose-built classpath tools.
  • As the `jvmsrc` CLI – Same engine, scriptable, pipe-friendly, and useful on its own when you just want to read a class.

Claude Code resolving HandlerInterceptor signatures via jvmsrc — 3 calls, correct answer, no cache walking.


What it saves, daily

On JVM projects with private libraries and no public Javadocs, jvmsrc is a force multiplier:

  • ~50K tokens saved per "what's on this external class" investigation — roughly 70% reduction in cost.
  • 15+ agent panic loops avoided daily — no grinding through Gradle caches, opening wrong JARs, or giving up.
  • Unlock delegation for complex tasks touching internal SDKs that you previously had to do yourself.

The Difference in Action

Without jvmsrc (The 25-turn blind grind)

User: Override the audit hook from AbstractTradingService — is there a public utility method on it we should reuse?

Agent:

1. *Searches workspace for AbstractTradingService.java* ➔ 0 hits

2. *Runs:* find ~/.gradle -name "trading-core*"

3. *Finds 4 versions:* 2.1.0, 2.3.0, 2.4.1, 3.0.0-SNAPSHOT

4. *Guesses:* Picks trading-core-2.4.1.jar (the project actually uses 3.0.0-SNAPSHOT!)

5. *Runs:* jar tf and javap -p on the wrong JAR

6. [22 turns later] *"I don't see a utility method, you'll have to implement it yourself."*

Reality: 3.0.0-SNAPSHOT added maskSensitiveFields() as a protected helper exactly for this case. The agent didn't hallucinate — it was just blind.

With jvmsrc (The 3-turn instant resolution)

User: Override the audit hook from AbstractTradingService — is there a public utility method on it we should reuse?

Agent:

1. search_classes("AbstractTradingService") ➔ Finds FQN & exact resolved library.

2. get_class_structure(scope: "overview") ➔ Discovers maskSensitiveFields() in 3.0.0-SNAPSHOT.

3. get_method_signature("maskSensitiveFields") ➔ Gets accurate signature and generics.

Result: Writes the override correctly on the first try. No cache walking, no guessing, no wrong version.


How It Works

  1. Build Tool Inquiry: jvmsrc queries your active build tool (e.g., Gradle) for the exact resolved classpath configuration.
  2. Intelligent Caching: It caches the resolved classpath, tracking changes to build files to stay current.
  3. Precision AI Tools: Instead of full-code dumping, it exposes precise, high-granularity tools (signatures, structure, search) to keep context windows small and token usage ultra-low.

Installation & Quick Start

1. Install CLI
npm install -g jvmsrc

Or use it directly via npx:

npx jvmsrc mcp

[!IMPORTANT]

Requires Node ≥ 20 and Java on `PATH` (for CFR decompiler + javap).

2. Add the MCP server

Paste this into your AI assistant config (Cursor, Claude Code, Windsurf, etc.), then restart the host:

{

"mcpServers": { "jvmsrc": { "command": "jvmsrc", "args": ["mcp"] } } }

Optional: jvmsrc config (or jvmsrc config --project /path/to/gradle-project) prints a paste-ready block plus environment hints. Most users can skip it and copy the snippet above.


MCP Server Reference

The MCP server runs over stdio via jvmsrc mcp. The default config needs no environment variables:

{

"mcpServers": { "jvmsrc": { "command": "jvmsrc", "args": ["mcp"] } } }

Private repository credentials (optional)

Only needed when your Gradle build requires credential env vars for a private Maven/Artifactory/Nexus-style repo. MCP hosts often do not inherit your interactive shell, so those vars must be set on the jvmsrc MCP process (then restart the server).

REPO_USER / REPO_PASS below are sample names only — they are not required by jvmsrc. Use whatever variable names your project’s Gradle scripts document:

{

"mcpServers": { "jvmsrc": { "command": "jvmsrc", "args": ["mcp"], "env": { "REPO_USER": "your-username", "REPO_PASS": "your-password" } } } }

Omit the env block entirely when the project does not need them.

Tools your agent gets
ToolWhat it does
`search_classes`Find a class by simple name or glob; returns compact FQN + lib name lists
`get_class_structure`Retrieves class overview (purpose + method names) or declared signatures
`get_method_signature`Fetches real overloads for a method, with parameter names and generics
`find_in_class_source`Performs regex or substring searches inside a resolved class
`get_class_source`Retrieves method bodies or line ranges (used as a last resort)
`search_in_artifact`Greps text across all classes in one resolved dependency JAR
`resolve_dependencies`Analyzes the actual dependency graph this project uses

[!TIP]

Every source response includes sourceAvailable: true for real sources (Javadoc, parameter names, generics), false for CFR decompilation (structure reliable, names may be synthetic).

[!NOTE]

Multimodule: omit modulePath and jvmsrc auto-picks the unique owning module; on a miss it lists candidate modulePaths. Methods: search_classes matches declared method names when the index has source enrichment; for body text in a known JAR use search_in_artifact. get_class_source methodNames also walks superclasses for unmatched names.

Make your agent use it

Tool descriptions help, but a built-in Bash tool the agent already trusts will often win. Two small additions make jvmsrc the default for dependency questions.

1. Add a rule to your agent's instructions (CLAUDE.md, AGENTS.md, Cursor rules) — many clients do not show MCP server instructions at all:

## Dependencies (jvmsrc)

For any question about a third-party library class, method or version, use the jvmsrc MCP tools (search_classes → get_class_structure → get_class_source with methodNames; resolve_dependencies for versions). When working inside one module, pass modulePath (':app' or the file you are editing) to get that module's versions. Never use javap, unzip/jar on JARs, or ~/.gradle/caches. Code under this repo's src/ → grep/read as usual.

2. (Claude Code) Block the shell fallbacks with a hook. docs/hooks/block-jvm-fallbacks.mjs denies javap, unzip/jar on JARs, and ~/.gradle/caches / ~/.m2 access, and tells the agent to use jvmsrc instead, so it redirects instead of silently reading the wrong version. Save the script somewhere stable and add to .claude/settings.json (project) or ~/.claude/settings.json (all projects):

{

"hooks": { "PreToolUse": [ { "matcher": "Bash", "hooks": [{ "type": "command", "command": "node /absolute/path/to/block-jvm-fallbacks.mjs" }] } ] } }

Set JVMSRC_HOOK_DISABLE=1 to switch it off temporarily. Other clients have their own hook mechanisms; check their current docs before porting.

Check that your client shows the server instructions: ask the agent *"What instructions does the jvmsrc MCP server give?"*. If it cannot answer, rely on the rule in step 1.

[!NOTE]

Inputs are forgiving. projectRoot can be omitted (the workspace is used, or set JVMSRC_PROJECT_ROOT); modulePath accepts app, /app, :app, or a file/directory inside the module (omit it, or pass "*", to search all modules); className accepts a simple name, Outer.Inner, or a trailing .class/.java. The first call on a project runs Gradle (typically 5–10s); later calls use the cache. Pass forceRefresh: true only after something changed that the build files do not show, such as a SNAPSHOT republish.


How It Compares

ToolApproachGap
Cache Indexers / ~/.gradle grepScan global cachesNo per-project resolved version
Static Parsers (e.g., build.gradle parser)Parse declarations onlyMisses transitive dependencies, BOMs, dynamic versions
`mcp-javadoc` / path-only CFRUser supplies manual JAR pathsNo automatic build/classpath resolution
Gradle MCP (Tooling API)Task/build focusedNot optimized for classpath-accurate FQN source lookup
`jvmsrc`Queries actual build tool & cachesVersion-correct sources and signatures for agents

Target Audience

Primarily Java + Spring Boot projects on Gradle. Other JVM languages (Kotlin, Scala) and Android work today on a best-effort basis and are on the roadmap as first-class targets — see ROADMAP.md.

*If you're on Maven or Bazel, it's planned but not shipping yet. Star the repo or open an issue and I'll prioritize accordingly.*


Detailed Reference

Requirements & Compatibility

Runtime: Node.js ≥ 20, Java on PATH.

Project types: JVM codebases (Java, Kotlin, Scala, Groovy). jvmsrc calls the build tool, not your editor.

Build systemStatus
GradleSupported — multimodule included
Maven, BazelPlanned (SPEC.md)

Point -p / projectRoot at the Gradle root (settings.gradle(.kts) or root build.gradle(.kts)). Uses ./gradlew when present, else gradle on PATH. Maven-only trees get an explicit unsupported error.

Known Limitations

Early software; the supported path is narrow:

AreaToday
Build toolGradle only
IntegrationGroovy init script (--init-script) — not a Gradle Portal plugin
ClasspathsStandard JVM + Kotlin MPP jvm* configurations when Gradle exposes them
OutputJava-shaped .java text (sources JAR, inter-project src, or CFR)

Composite builds, Android-only layouts, and exotic configurations are not fully validated. See ROADMAP.md.

Security & Privacy

  • No telemetry.
  • Local only — caches and diagnostics stay on disk; never writes under your project root.
  • Subprocesses via argv only (no shell interpolation) — see SECURITY.md.
  • Optional JVMSRC_ALLOWED_ROOTS to lock down which projects

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx