pzalutski-pixel/javalens-mcp

Overview

This is an MCP server that gives AI agents semantic understanding of Java codebases using Eclipse JDT. It exposes tools for navigation, refactoring, search, and metrics so agents can perform structured code analysis.

Best for

Best for
Java developers building or extending AI-assisted coding workflows that need deep code understanding.

Use cases

• AI-assisted code navigation and class hierarchy exploration
• Automated Java refactoring suggestions within an MCP-aware editor
• Semantic search across a Java project for symbols and references

How to use

Install

npx -y javalens-mcp

Tools exposed

• search_symbols
• go_to_definition
• find_references
• find_implementations
• get_type_hierarchy
• get_document_symbols
• get_symbol_info
• get_type_at_position
• get_method_at_position
• get_field_at_position
• find_annotation_usages
• find_type_instantiations
• find_casts
• find_instanceof_checks
• find_throws_declarations
• find_catch_blocks
• find_method_references
• find_type_arguments
• find_reflection_usage
• get_diagnostics

Tested with

Claude Code, Cursor

Example client config

{\n  "mcpServers": {\n    "javalens": {\n      "command": "java",\n      "args": ["-jar", "/path/to/javalens/javalens.jar", "-data", "/path/to/javalens-workspaces"],\n      "env": {\n        "JAVA_PROJECT_PATH": "/path/to/your/java/project"\n      }\n    }\n  }\n}

Notes

This is an MCP server that gives AI agents semantic understanding of Java codebases using Eclipse JDT. It exposes tools for navigation, refactoring, search, and metrics so agents can perform structured code analysis.

29 stars on GitHub. Last updated 2026-05-29. Licensed MIT.

Use cases

• AI-assisted code navigation and class hierarchy exploration
• Automated Java refactoring suggestions within an MCP-aware editor
• Semantic search across a Java project for symbols and references

Pros

• Leverages Eclipse JDT for accurate Java semantics
• Provides concrete analysis tools directly to AI agents
• Lightweight integration via MCP protocol

Cons

• Limited to Java projects only
• Small community and low star count may mean less support
• Requires MCP-compatible client or agent setup

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.