mcp-steroid
Provides Claude with full IDE capabilities—syntax highlighting, refactoring, navigation, linting—reducing context loss and enabling accurate modifications ac…
Open-source JetBrains incubator MCP server that runs inside IntelliJ-family IDEs and exposes the IntelliJ Platform to AI agents: semantic code navigation, refactorings, inspections, test running, debugging, and visual IDE awareness through screenshots and UI automation. Install as an IDE plugin, or use the preview devrig CLI to bridge any MCP-capable agent to every IDE you have open.
- Ask Claude to refactor a specific function while viewing the entire project structure and dependencies.
- Generate test cases for a module by analyzing its actual implementation and related code files.
- Find unused variables across multiple files by running IDE inspection tools through Claude.
Provides Claude with full IDE capabilities—syntax highlighting, refactoring, navigation, linting—reducing context loss and enabling accurate modifications across large codebases without manual file juggling.
Development teams managing complex multi-file projects needing AI-assisted refactoring and code analysis at IDE-level fidelity.
https://github.com/jonnyzzz/mcp-steroid
By jonnyzzz
How to Get It
Install the 'MCP Steroid' plugin from JetBrains Marketplace: Settings > Plugins > Marketplace, search 'MCP Steroid' (or https://plugins.jetbrains.com/plugin/30019-mcp-steroid). For faster updates add the custom repository https://mcp-steroid.jonnyzzz.com/updatePlugins.xml
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Once it’s connected, paste this into Claude:
Refactor a specific function while viewing the entire project structure and dependencies
Trust Signals Auto-scanned
Data & Access
Community Pulse Active
Discussed on Hacker News
- MCP Steroid – Give AI the whole IDE, not just the files — Hacker News · 10 pts
1 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 49 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 49 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.