langchain4j-mcp-server-patterns
Provides Model Context Protocol (MCP) server implementation patterns with LangChain4j. Use when building MCP servers to extend AI capabilities with custom tools, resources, and prompt templates.
Оригинален текст · няма потвърден превод на българскиПърво прочетете инструкцията.
Файлът се зарежда от посочения източник само по ваше действие. Можете да го прочетете тук, да го копирате или да го запазите като .md.
GitHub хранилище- Звезди на репото
- 348
- Лиценз
- Не е посочен. Проверете в репозитория.
- Последна проверка на записа
- Няма посочена дата
Добавете в своя инструмент.
Командата отваря избора на skills от репозитория. Прочетете файла и условията на автора преди изпълнение.
npx skills add giuseppe-trisciuoglio/developer-kitСтраницата копира текст. Не инсталира и не изпълнява нищо на устройството ви.
Откъс от SKILL.md
Началото на файла на автора, без превод.
LangChain4j MCP Server Implementation Patterns
Overview
Use this skill to design and implement Model Context Protocol (MCP) integrations with LangChain4j.
The main concerns are:
- defining a clean tool, resource, and prompt surface
- choosing the right transport and bootstrap model
- filtering unsafe capabilities before exposing them to agents or applications
Keep SKILL.md focused on the implementation flow. Use the bundled references for expanded examples and API-level detail.
When to Use
Use this skill when:
- building a Java MCP server that exposes tools, resources, or prompts
- integrating LangChain4j with one or more external MCP servers
- wiring MCP support into a Spring Boot application
- filtering available tools by tenant, user role, or runtime context
- adding observability, resilience, and safe failure handling around MCP interactions
- reviewing an MCP integration for prompt-injection and side-effect risks
Typical trigger phrases include langchain4j mcp, java mcp server, mcp tool provider, spring boot mcp, and connect langchain4j to mcp.
Instructions
1. Design the MCP surface before writing code
Decide what the server should expose:
- tools for actions with clear inputs and side effects
- resources for read-only or structured data access
- prompts only when a reusable template adds real value
Keep names stable, descriptions concrete, and schemas small enough for a client or model to understand quickly.
2. Implement providers with narrow responsibilities
Use separate classes for each concern:
- tool provider for executable functions
- resource provider for discoverable and readable data
- prompt provider for reusable prompt templates
Validate arguments before execution and return clear error messages for invalid input or unavailable dependencies.
3. Choose the transport intentionally
Use:
- stdio for local integrations, CLI tools, and sidecar processes
- HTTP or SSE for remote or shared services
Pin external server versions and document how the process is started, authenticated, and monitored.
4. Bridge MCP into LangChain4j carefully
When consuming MCP servers from LangChain4j:
- initialize clients during application startup
- cache tool lists only when stale metadata is acceptable
- filter tools by trust level, environment, or user permissions
- fail closed for dangerous tools rather than exposing everything by default