Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add plugins/fgforrest/mcp-jdwp-java/marketplace/plugin marketplace add FgForrest/mcp-jdwp-javagit clone --depth 1 https://github.com/FgForrest/mcp-jdwp-javaGrade A, and why
mcp-jdwp-java scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- jdwp-debugging — 86% identical, 25 lines differ
What it actually says
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "mcp-jdwp-java",
"description": "Java JDWP debugger plugin for Claude Code",
"version": "2.10.1",
"owner": {
"name": "FG Forrest"
},
"plugins": [
{
"name": "jdwp-debugging",
"description": "Java JDWP debugger via MCP — set breakpoints, inspect runtime state, evaluate expressions, mutate variables, catch exceptions at throw site, trace execution with logpoints.",
"version": "2.10.1",
"author": {
"name": "Jan (Novoj) Novotný"
},
"source": "./",
"category": "development",
"tags": ["java", "debugging", "jdwp", "jdi", "breakpoints", "mcp"]
}
]
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 23 lines scan A 43136dba4f10
mcp-jdwp-java is a plugin published in the GitHub repository FgForrest/mcp-jdwp-java (24 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
java-agent-debugger
Interactive Java debugging for AI agents via the jdbg CLI (a native, cross-platform wrapper around the JDK's jdb).
java-agent-debugger
Debug Java programs interactively from the command line via the jdbg CLI: launch a program or attach to a running JVM (JDWP), set breakpoints, step through code, and inspect variables, expressions, threads, and exceptions. Stateful background sessions with structured (text/JSON) output. Cross-platform, native on…
fixture-monkey
Claude Code plugins for Fixture Monkey.
memind-plugins
Official Memind integrations for Claude Code.
developer-kit-ai
AI/ML capabilities including prompt engineering, RAG, and chunking strategies.
jaipilot
Plugin marketplace listing 1 plugin: jaipilot.