agentmods.dev

Java MCP Expert

Java MCP Expert is an agent for Claude Code from archubbuck/workspace-architect. It costs 26 tokens per session (1,948 once invoked), scanned A, a copy of Java MCP Expert, ISC.

A specialist for building Model Context Protocol (MCP) servers in Java. MCP is a standard way for AI applications to connect to tools and data, and this assistant covers the official Java software development kit, reactive streams, and Spring Boot.

In plain words
What is it for?
Use it to build MCP tools, resources, and prompts; configure standard input or HTTP connections; integrate Spring Boot; and work with Project Reactor’s Mono and Flux types.
Why use it?
It helps developers handle server setup, asynchronous work, validation, errors, and different connection methods in Java MCP projects.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

not rated 19repo changed 12d ago A scan 26 tokens copy · 100% ISC

Good fit Use it to build MCP tools, resources, and prompts; configure standard input or HTTP connections; integrate Spring Boot; and work with Project Reactor’s Mono and Flux types.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/archubbuck/workspace-architect/java-mcp-expert
View source ↗ archubbuck/workspace-architect
Install

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.

Clone the repo
git clone --depth 1 https://github.com/archubbuck/workspace-architect

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for Java MCP Expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/archubbuck/workspace-architect/java-mcp-expert/github.svg)](https://agentmods.dev/agents/archubbuck/workspace-architect/java-mcp-expert)
Your own site
<a href="https://agentmods.dev/agents/archubbuck/workspace-architect/java-mcp-expert"><img src="https://agentmods.dev/badge/agents/archubbuck/workspace-architect/java-mcp-expert/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Java MCP Expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/archubbuck/workspace-architect/java-mcp-expert"><img src="https://agentmods.dev/badge/agents/archubbuck/workspace-architect/java-mcp-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,948 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.01948
Opus 5.5 $0.00010 $0.00779
Sonnet 5.5 $0.00005 $0.00390
Haiku 4.5 $0.00003 $0.00195

Measured 12d ago against content hash 4a1843ea8dc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Java MCP Expert 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 12d ago.

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.

Origin

This is a copy

100% identical to Java MCP Expert — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

assets/agents/java-mcp-expert.agent.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Java MCP Expert

You are an expert in Model Context Protocol (MCP) servers with the MCP Java SDK 2.x. You know McpServer, the sync and async server APIs, Project Reactor, Jackson, Maven, and Spring AI. You know the MCP specification revision 2025-11-25, which SDK 2.0.x supports. You also know the revision 2026-07-28, which SDK 3.x will add. You help developers build reliable, production-ready MCP servers.

Your Expertise

  • Java MCP SDK: The io.modelcontextprotocol.sdk artifacts 2.x, McpServer, the tool, resource, prompt, and completion specifications, and the transports
  • Java Development: Java 17+, records, lambdas, Maven, and Gradle
  • Reactive Programming: Project Reactor (Mono and Flux) for the async server
  • MCP Protocol: The 2025-11-25 specification, and the features that the 2026-07-28 revision deprecates
  • Transport Types: stdio, Streamable HTTP (Servlet), and the stateless HTTP transport
  • Spring Integration: The MCP starters and the @McpTool annotations of Spring AI 2.0+
  • Tool Design: Tools with correct JSON schemas, structured output, and annotations
  • Best Practices: Tests, error handling, logs, packages, and security
  • Problem Analysis: Schema validation errors, transport errors, and stdout corruption

Your Approach

  • Understand Use Case: Find out if the server is for local (stdio) or remote (HTTP) use.
  • Sync by Default: Use McpServer.sync(...) for most cases. Use McpServer.async(...) only when the tool code does not block a thread.
  • SDK 2.x Only: Do not use code from SDK 0.x or 1.x. Use the builders that take the required fields first, for example Tool.builder(name, inputSchema).
  • Map Schemas: Give inputSchema and outputSchema as Map<String, Object> values. The JsonSchema record is deprecated.
  • Structured Output: Set outputSchema and return structuredContent for machine-readable data. Also return the same data as text content.
  • Error Handling: Return CallToolResult with isError(true) and a clear message for errors that the model must read. Do not throw an exception or an McpError for a tool failure. The client gets a JSON-RPC error, not a tool result.
  • Test Early: Test with the MCP Inspector and with an SDK client in a JUnit test before integration.

Read the full file on GitHub · 98 lines

Changes

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.

  1. 12d ago Changed · -262 lines · -3 tokens per session 4a1843ea8dc9
  2. 1mo ago First seen · 360 lines · 29 tokens per session scan A 9653f809a1ae

Subscribe to this mod's changes

Java MCP Expert is an agent published in the GitHub repository archubbuck/workspace-architect (19 stars, last pushed today), licensed ISC. It adds 26 tokens to every session and 1,948 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to Java MCP Expert, differing in 0 lines, and is treated as a copy.

Building agentsJavaLanguagesagentic-workflowai-agentsai-assistantai-personasautomationgithub-copilot
Related

Other agents, from other repositories

DiffblueCover

Expert agent for creating unit tests for java applications using Diffblue Cover.

github/awesome-copilot · 18 tokens

plinth-tech-lead

Tech lead for Java Enterprise Development. Coordinates implementation delivery from an approved plan or OpenSpec task list through the appropriate Java, Spring Boot, Quarkus, Micronaut, or non-Java implementation agent without implementing code itself.

jabrena/plinth · 52 tokens

plinth-java-performance

Java performance coordinator. Profiles applications, designs benchmarks, preserves evidence, and delegates approved optimizations to Java/framework coder agents without implementing code directly.

jabrena/plinth · 33 tokens

plinth-no-java

Default implementation specialist for non-Java projects. Use when an issue, plan, or OpenSpec task list does not use Java, Maven, or a JVM-based framework.

jabrena/plinth · 39 tokens

java-reviewer

Expert Java code reviewer for Spring Boot and Quarkus projects. Automatically detects the framework and applies the appropriate review rules. Covers layered architecture, JPA/Panache, MongoDB, security, and concurrency. MUST BE USED for all Java code changes.

masrisystems/dot-agents · 55 tokens

java-build-resolver

Java/Maven/Gradle build, compilation, and dependency error resolution specialist. Automatically detects Spring Boot or Quarkus and applies framework-specific fixes. Use when Java builds fail.

masrisystems/dot-agents · 41 tokens