Bevy BRP MCP

- Update your dependencies to use the crate from the new location
- All existing functionality has been preserved
- The crate is still published to crates.io asbevy_brp_mcp

A Model Context Protocol (MCP) server that enables AI coding assistants to control launch, inspect and mutate Bevy applications via the Bevy Remote Protocol (BRP). This tool bridges the gap between coding agents and Bevy by providing comprehensive BRP integration as an MCP server.

The bevy_brp_mcp crate follows Bevy's version numbering and releases new versions for each Bevy release.

- Entity Management: Create, destroy, query, and modify entities
- Component Operations: Get, insert, remove, and mutate components on entities
- Resource Management: Access and modify global resources
- Query System: Advanced entity querying with filters
- Hierarchy Operations: Parent-child entity relationships

- App Discovery: Find and list Bevy applications in your workspace
- Build Status: Check which apps are built and ready to run
- Launch Management: Start apps with proper asset loading and logging
- Example Support: Discover and run Bevy examples from your projects

- Component Watching: Monitor component changes on specific entities
- Log Management: Centralized logging for all launched applications
- Process Status: Check if apps are running with BRP enabled

- Format Discovery: Get correct JSON formats for BRP operations (via bevy_brp_extras)
- Screenshot Capture: Take screenshots of running Bevy applications
- Keyboard Input: Send keyboard input to Bevy applications for testing and automation
- Key Code Discovery: List all available keyboard key codes for input operations
- Graceful Shutdown: Clean application termination

first, install via cargo:cargo install bevy_brp_mcp

configure your mcp server - for claude code this would be in the~/.claude.jsonfile.

use bevy::prelude::; use bevy_brp_extras::BrpExtrasPlugin; fn main() { App::new() .add_plugins(DefaultPlugins) .add_plugins(BrpExtrasPlugin) // Enhanced BRP features .run(); }

In either case you'll need to make sure to enable bevy's "bevy_remote" feature.

If you have bevy_brp_extras installed, it can get the type information directly from the running app andand provide it if queried via brp_extras/discover_format - or it will provide it in the error message if your coding agent tries a call and fails.
- Discovery: Uselist_bevy_appsto find available applications
- Launch: Uselaunch_bevy_appto start your game with proper logging
- Inspect: Usebevy_queryto find entities of interest
- Monitor: Usebrp_get_watchto observe entity changes in real-time
- Modify: Usebevy_mutate_componentto adjust entity properties
- Debug: Useread_logto examine application output
- Capture: Usebrp_extras_screenshotto document current state
- Interact: Usebrp_extras_send_keysto send keyboard input for testing

All launched applications create detailed log files in/tmp/with names like:

- bevy_brp_mcp_myapp_1234567890.log(application logs)
- bevy_brp_mcp_watch_123_get_456_1234567890.log(monitoring logs)

Use the log management tools to view and clean up these files.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

An MCP server for AI coding assistants to control, inspect, and modify Bevy applications using the Bevy Remote Protocol (BRP).

A server for Ebitengine games that provides debugging and recording tools by capturing game state.

Fennara MCP connects AI agents like Codex, Cursor, Claude Code, and Claude Desktop to Godot-aware tools for real Godot projects. It focuses on feedback from Godot: GDScript diagnostics, scene validation, runtime errors, scene inspection, node properties, screenshots, SemanticSearch, and patch-and-rerun workflows.

The most comprehensive MCP server for Godot Engine. 95+ tools for scene management, GDScript LSP, DAP debugging, screenshot capture, input injection, and CC0 asset library.

AI-powered live runtime debugging with Lightrun production context.

Run, debug, and triage tests via natural language across HyperExecute, Automation, SmartUI, and Accessibility on the TestMu AI cloud.

Understand, develop, and debug authorization policies in Oso Cloud.

A comprehensive proxy that combines multiple MCP servers into a single MCP. It provides discovery and management of tools, prompts, resources, and templates across servers, plus a playground for debugging when building MCP servers.

Proxyman MCP allows AI to inspect HTTP traffic, create debugging rules, and control Proxyman - all through natural language conversations.